News for hackers. Stuff that matters.
Re:AMD acquires Taalas to boost inference performance by etc... by anthonypasq on Thursday August 06, 2026 @05:56PM (#49203160)
Personally I think Apple should have acquired them. if you could burn a gemma4 class model into an iphone and actually get extremely low latency and low battery usage it would feel like the future IMO. even if it means you wont get frontier intelligence, there might actually be incentive to buy a new mobile device every year again.
Re:AMD acquires Taalas to boost inference performance by etc... by Melatonic on Thursday August 06, 2026 @06:34PM (#49203553)
The Taalas chips are not physically small. And part of their secret (if you look at the design) is just locating a bunch of memory soldered on the edges ( I belive higher amounts of SRAM ? )
Re:AMD acquires Taalas to boost inference performance by etc... by chorizo on Thursday August 06, 2026 @08:39PM (#49204555)
Baking the base models on to ROM makes a lot of economic sense. SRAM for the KV cache & fine-tunes, not so much. Sure you’d get incredible speeds but it’s not scalable from a die-size or cost perspective.

Rather base model on ROM + KV cache on DRAM is much more scalable. Also this would work great for edge devices that have a 2-5 year lifecycle.

Re:AMD acquires Taalas to boost inference performance by etc... by adrianN on Thursday August 06, 2026 @11:00PM (#49205462)
It is my understanding that just baking the model itself into silicon only gives moderate gains because memory bandwidth remains a bottleneck.
Re:AMD acquires Taalas to boost inference performance by etc... by chorizo on Thursday August 06, 2026 @11:07PM (#49205501)
The big benefit is ROM cells require fewer components than DRAM. So the chips would be tiny, dense, cheap and consume far less power.
Re:AMD acquires Taalas to boost inference performance by etc... by klodolph on Thursday August 06, 2026 @11:38PM (#49205670)
I thought DRAM was pretty dense already. Is mask ROM that much denser?
Re:AMD acquires Taalas to boost inference performance by etc... by chorizo on Thursday August 06, 2026 @11:50PM (#49205716)
Yes, each rom bit can be a transistor or even a diode with a decoder circuit. Simplest Dram cell is capacitor+transistor - and you need a clock, refresh circuit etc.

Someday, I imagine model weights could even be encoded as analog resistors (memristors or similar) for even greater density

Re:AMD acquires Taalas to boost inference performance by etc... by ReactiveJelly on Friday August 07, 2026 @12:41AM (#49205960)
Hm. I wonder how many relays I'd need to make a physical MNIST classifier. That'd be dope
Re:AMD acquires Taalas to boost inference performance by etc... by Tuna-Fish on Friday August 07, 2026 @08:58AM (#49209732)
It's not even just that. If you just built the rom chips separately and swapped them for the RAM of a normal accelerator, it would not help at all.

The trick is that every compute element in their system has it's own small pool of ROM, instead of putting all the ram behind a common pipe. ROM is just used because it's the densest kind of memory that can be fabricated on the same process as their logic.

Re:AMD acquires Taalas to boost inference performance by etc... by lelanthran on Friday August 07, 2026 @02:03AM (#49206422)
Did you try using the the talaas chat? Something stupid like 18k tokens/second.

Think it's called Askjimmy or similar.

Re:AMD acquires Taalas to boost inference performance by etc... by TeMPOraL on Friday August 07, 2026 @03:52AM (#49207203)
What is the model they're using there though? Interrogated, it claims it's a BERT variant and has capabilities around GPT-3 and below GPT-4.

(Not that I believe it, it writes too well for GPT-3.)

Hosted frontier models from two years ago would be much faster today, too.

Re:AMD acquires Taalas to boost inference performance by etc... by egorfine on Friday August 07, 2026 @04:18AM (#49207373)
They run Llama 3.1 8B.
Re:AMD acquires Taalas to boost inference performance by etc... by jgilias on Friday August 07, 2026 @02:16AM (#49206536)
Oh boy, thanks for sharing this, truly mind blowing. It was chatjimmy.ai
Re:AMD acquires Taalas to boost inference performance by etc... by onion2k on Friday August 07, 2026 @01:13AM (#49206105)
Baking the base models on to ROM makes a lot of economic sense.

Less so for consumers though, because it'd mean the phone is out of date in 3 months when a better model comes along.

Re:AMD acquires Taalas to boost inference performance by etc... by ronsor on Friday August 07, 2026 @01:15AM (#49206118)
It's a perfect reason to get consumers to buy a new phone every year again! They got bored of the camera.
Re:AMD acquires Taalas to boost inference performance by etc... by miohtama on Friday August 07, 2026 @02:55AM (#49206823)
This stopped working some years ago.

Now you sell the same phone with higher price tag.

Re:AMD acquires Taalas to boost inference performance by etc... by ben_w on Friday August 07, 2026 @06:26AM (#49208298)
Right now the models are doubling in performance (by the METR time horizon metric at least) every 4 months, so 3 doublings in a year; conversely, I hear (not my field) it takes around a year to make a prototype IC and another year to turn that into mass production, i.e. if the next (late-2026 model) iPhone has a chip like this, it will likely be with, at best, a late-2024 set of weights. I think you can get open-weights models today that have performance equivalent to the SOTA-late-2024 while fitting in the RAM of a (high end) 2025-26 phone.

At some point the music will stop on training bigger models, and when that happens it will make sense to have ROM weights (or 100% analog circuits given how noise-resistant LLMs are), but we'll know when that is because the investment bubble funding the training of new models will have burst.

Re:AMD acquires Taalas to boost inference performance by etc... by close04 on Friday August 07, 2026 @07:49AM (#49208982)
At some point it’s got to be good enough for the normal “phone stuff” that appeal to most users. So they wouldn’t suffer from FOMO because they didn’t wait for the next model. Every phone gimmick went through the same evolution curve until it passed the “good enough” point and eventually plateaued.
Re:AMD acquires Taalas to boost inference performance by etc... by ben_w on Friday August 07, 2026 @07:55AM (#49209039)
Yes, but irrelevant. While these models are improving at the present rate, the manufacturer can save money at no loss of feature-bullet-point-on-website by letting you download a model after you bought the thing and running it on normal hardware.

The rate of change to the models has to be slower than the hardware roll-out to be worth a hardware solution. If "good enough" happens before then, that just means the user gets a software solution.

Re:AMD acquires Taalas to boost inference performance by etc... by close04 on Friday August 07, 2026 @10:36AM (#49211138)
You might be right but hard to tell without analyzing costs and benefits. Is a cutting edge model for phone stuff worth the slower performance and battery drain for example?

The rate of change by itself doesn’t tell you the whole story because of costs and diminishing returns. So what if your model is twice as good if it’s 10x the cost and it saves you 1ms? Everything else about phones reached “good enough for a phone” levels in years, and then got minimal generational improvements.

Re:AMD acquires Taalas to boost inference performance by etc... by dgrabla on Friday August 07, 2026 @09:05AM (#49209802)
wait, analog circuits? can you elaborate this?
Re:AMD acquires Taalas to boost inference performance by etc... by ben_w on Friday August 07, 2026 @09:14AM (#49209908)
Transistors can be used to amplify signals, they are not limited to acting as binary switches. If you use analog rather than digital, using transistors in this way means you can replace however many transistors it would have taken for multiplying two n-bit numbers with just one; I understand capacitors can be used for accumulation, but don't know how many additional components that needs as I'm an electronics noob.

The reason we don't do this in general (any more) is that for long chains between input and output it has been much too difficult to avoid accumulation of errors. LLMs happen to be extremely resilient to errors like this, which is also why we can use e.g. 4-bit weights.

Re:AMD acquires Taalas to boost inference performance by etc... by inigyou on Friday August 07, 2026 @09:09AM (#49209856)
Circuits that aren't restricted to two particular voltage levels.
Re:AMD acquires Taalas to boost inference performance by etc... by fsloth on Friday August 07, 2026 @02:11AM (#49206486)
I don’t think average user _needs_ to solve frontier challenges. ”Call to Jane”, ”turn on the lights” and ”what’s the weather this afternoon” is more like it I would guess.

Ofc if the model has some critical bugs that’s another matter.

Re:AMD acquires Taalas to boost inference performance by etc... by dzhiurgis on Friday August 07, 2026 @02:50AM (#49206782)
Your examples worked on phones for over a decade.

Maybe baking in a model that is "certified" to have some unconditioned truths + rest is pulled from external models/store could make sense. But AFAIK that doesn't exist and I'm not sure it can possibly be made. Perhaps society as a whole at least can work on an open corpus of training data, but I'm not holding my breath on this.

Re:AMD acquires Taalas to boost inference performance by etc... by gf000 on Friday August 07, 2026 @03:52AM (#49207199)
It barely works even today, like Siri is laughably bad.
Re:AMD acquires Taalas to boost inference performance by etc... by dzhiurgis on Friday August 07, 2026 @04:19AM (#49207374)
I mean the examples he gave definitely work. Mostly well I'd say as they are pretty primitive.

What Siri is missing is more logical solutions and answers for recipes, etc (still suck even with chatgpt integration).

Re:AMD acquires Taalas to boost inference performance by etc... by darkwater on Friday August 07, 2026 @05:05AM (#49207752)
No, they don't work. Just asked Siri the other day "what's the weather tomorrow in $LOCATION" (where $LOCATION is a broader zone and not strictly a city) and the answer was the weather in a street called "$LOCATION Avenue" in a city 150km away.
Re:AMD acquires Taalas to boost inference performance by etc... by gf000 on Friday August 07, 2026 @04:49AM (#49207598)
Works, sometimes. But they can fail spectacularly and unexpectedly even on very basic questions/instructions, like so simple that a hand-coded word-matching style logic could get them right 20 years ago.
Re:AMD acquires Taalas to boost inference performance by etc... by logicallee on Friday August 07, 2026 @03:40AM (#49207105)
>Your examples worked on phones for over a decade.

Nope. And not only not a decade ago, right now.

If you have an Android or iPhone, you can give it clear and easy to understand instructions that Gemma 4 could complete[1] if it had tool calls on it, and that 100.00% of Claude, ChatGPT, Grok, Kimi, you name it, could understand and all complete if they had the access.

The phones will fail to complete it. I just tried Siri. I said "hey Siri", waited for Siri to come up, and then I asked one of the exact sentences you replied to: "what's the weather this afternoon?" It thought for around 20 seconds, and said "Something went wrong. Please try again."[2]

I have Wifi, I have mobile Internet, I have free storage space, I have up to date software. What went wrong is that phones have never properly connected agents, not ten years ago, not last year, not this year, and probably not next year.

But don't settle for what Google could do in 1999 by hotlinking the keyword "weather" in any query to the weather being shown in the results.

Tell your phone (any phone): "Please call back the last number that called me that is not an unlisted number, regardless of who it came from."

0 out of any phone will complete that today, tomorrow, a year from now, five years from now, ever, because phone makers are not going to let them do that.

Meanwhile, 100% of all frontier agents could complete it if they had tool calls on the phone. Which they don't, and won't ever, thanks to the duopoly.

Okay, that's a bit dismissive, I would love to be wrong!

[1] after any voice recognition to text - which does work really well on both Android and iPhone! [2] screenshot: https://ibb.co/21rtDnfV

Re:AMD acquires Taalas to boost inference performance by etc... by narism on Friday August 07, 2026 @07:30AM (#49208792)
I’m on the IOS 27 beta and Siri did those two tasks (weather/phone) flawlessly. It’s a lot better than it used to be.
Re:AMD acquires Taalas to boost inference performance by etc... by logicallee on Friday August 07, 2026 @07:58AM (#49209071)
Thanks for trying that! Very interesting.

Can you say this to it: "Hey Siri [wait for it to come up] - please send me an email with the temperature right now so I have it for my records." and see if it can complete the task without any backtalk or misunderstanding, and if you get exactly what you asked for. (It's a really clear request.) Should be 1 statement, no clarification, conversation, random search results, ("Here's what I found!"), etc.

A normal frontier model can do that - or Siri can do it if it is properly connected to Claude, ChatGPT, Gemini, Grok, or any other frontier AI - but previously it was never properly connected.

If it can do this task, I might have to look into this again. It counts as a success if it sends yourself any email with the current temperature and you actually get it (it can include whatever other text in the email), and a failure if it talks back, says "here's what I found", says it can't, asks you any question, sends you an email that doesn't actually contain the current temperature, just reads you the temperature and then asks if you want it to send an email, etc. Should be 1 shot.

let me know if it works!

Re:AMD acquires Taalas to boost inference performance by etc... by narism on Friday August 07, 2026 @09:24AM (#49210035)
It brings up a preview of the email and you have to tap or tell it to send it from there but otherwise it worked for this as well.

Subject: Current Temperature Body: The current temperature is 27°C in <my city>.

Re:AMD acquires Taalas to boost inference performance by etc... by logicallee on Friday August 07, 2026 @10:36AM (#49211141)
thanks! useful.
Re:AMD acquires Taalas to boost inference performance by etc... by fwip on Friday August 07, 2026 @09:55AM (#49210458)
In my experience, they had a lot of stuff working well in the first few years they rolled out the home voice assistants - Alexa, google home, etc. But for whatever reason, they've spent the last eight(?) years silently breaking things that used to work. Stuff like audiobook playing, music alarms, or even messaging people.

Once they started seeing useful (if niche) functionality as a cost center, there wasn't really a world in which these could usefully exist. Their big bet now seems to be that LLMs will lead them to profitability - but whether that's from increased data harvesting, cheaper integrations, or because it'll be useful enough to charge subscription fees, I couldn't tell you.

Re:AMD acquires Taalas to boost inference performance by etc... by yunwal on Friday August 07, 2026 @10:46AM (#49211296)
I just asked Siri

"Hey Siri, what's the weather in <nearby town with a generic name> tomorrow" and it gave me a town with the same name ~800 miles from me.

Re:AMD acquires Taalas to boost inference performance by etc... by chorizo on Friday August 07, 2026 @01:31AM (#49206221)
And the customers can wait for the new phone released next year. These are edge models - the average customer doesn’t need the latest frontier model. Just needs to be good enough for the features you promised.
Re:AMD acquires Taalas to boost inference performance by etc... by otabdeveloper4 on Friday August 07, 2026 @01:43AM (#49206289)
That's a software engineering problem. They just need to figure out how to fine-tune for alignment and tool usage.

That's the only thing the normie consumer cares for really.

Re:AMD acquires Taalas to boost inference performance by etc... by tesnorindian on Friday August 07, 2026 @02:27AM (#49206616)
We also have ReRAM (Analog Computing), which also holds a promising future given its efficiency and low power. Though ReRAM of larger size is still a research area.
Re:AMD acquires Taalas to boost inference performance by etc... by petra on Friday August 07, 2026 @03:00AM (#49206851)
AMD can let the SRAM be on a different chip. Maybe even something similar to their 3D cache. that could increase density to 20B[1]. They could also move from 6nm to 2nm. that would probably increase density by another 3x to 60B.

Add a bunch of chips together, and you get to a server that can run a 800B model, very fast and probably significantly cheaper than others.

[1]https://www.eetimes.com/taalas-specializes-to-extremes-for-e...

Re:AMD acquires Taalas to boost inference performance by etc... by coderbants on Friday August 07, 2026 @03:47AM (#49207160)
I think the lifecycle for these chips could stretch far longer. If you're offering these models on a two year lifecycle, then you'd be able to stand up your top tier (wouldn't need to be frontier) at high speed. Run (for example) Kimi K3 on it and give it a brand name:

AcmeAI Carbon

Market it as your premier (only) model at high throughput. Two years later you stand up MSICs for the new state of the art with entirely new hardware, your lineup becomes:

AcmeAI Nitrogen (top tier) AcmeAI Carbon (mid tier)

If you just kept pushing the same model down your pricing tier over time you could still extract a lot of value from an old model, even years after it's been set in stone. Working on brand new code/frameworks? Pay to use the newest model. Working on legacy code? Use the lower tier models that will already know your legacy frameworks, pay far less and still get massive throughput. I've worked on a lot of government projects that this would be absolutely brilliant for.

The other side of this is that agent harnesses are NOT set in stone, so even a legacy model with a knowledge cut-off that's years out of date can likely still be helped quite a bit by harness and fetch behaviours that are still developing rapidly. Especially at this kind of throughput.

Re:AMD acquires Taalas to boost inference performance by etc... by hypfer on Friday August 07, 2026 @04:38AM (#49207508)
I'm somewhat doubtful that we will be seeing something as large as Kimi K3 in silicon any time soon.

This tech can definitely scale up from the current 8B prototype, but - at least as far as my limited understanding of the tech involved goes - you cannot just ASIC a trillion weights model due to physical size constraints.

___

Specification HC1

Model Llama 3.1 8B (hardwired)

Process TSMC 6nm

Die size 815mm²

___

So the current prototype already pushes the limits of what we can fit on a single die, and that is already likely going to limit your yield.

Re:AMD acquires Taalas to boost inference performance by etc... by A_D_E_P_T on Friday August 07, 2026 @05:27AM (#49207890)
Kimi K3 is huge, though. Deepseek V4 Flash is a much more moderate model (284B total), and it works extremely well. Models of that size, and smaller, are just going to keep getting better and better. Presumably there's a threshold below which models are not generally useful or competitive, but if models-on-silicon can scale up to just 256B, that would be really remarkable.
Re:AMD acquires Taalas to boost inference performance by etc... by momojo on Friday August 07, 2026 @11:51AM (#49212324)
My 2 cents to for your point:

- Deepseek V4 Flash is impressively capable. Sonnet still beats it out by a thin margin, but the real kicker is that a typical session with Sonnet at current API costs is ~$2. The same session with Deepseek is 2 cents (ha). Its even allowed me to consider offering free-with-limits API usage on my own app. - Taalas (or competitors) have a lot going for them. If anything I feel like they need to join hands with these smaller model makers and converge in 2028

Re:AMD acquires Taalas to boost inference performance by etc... by LarsDu88 on Friday August 07, 2026 @12:12PM (#49212669)
This is an architectural limitation that may be overcome by how you bake the MoE (mixture-of-experts) onto silicon.

If you could manage a per-die expert somehow and keep the expert routing gate relatively fast (through an interposer interconnect or doing wafer-scale Cerebras type shit) you don't need to keep the whole thing on the same die. Small dies with one expert per die on an interposer, and a very tiny router might be sufficient.

Re:AMD acquires Taalas to boost inference performance by etc... by to11mtm on Friday August 07, 2026 @12:49PM (#49213163)
There's in-betweens; '1T SRAM' or eDRAM.

Of course, 1T SRAM isn't really SRAM, but my understanding is it doesn't require external refresh like eDRAM, is a bit easier to fab on-die than eDRAM, and is half the mm2 per Megabit compared to real SRAM (15% more die size than eDRAM)...

Re:AMD acquires Taalas to boost inference performance by etc... by selcuka on Thursday August 06, 2026 @09:08PM (#49204725)
Their PoC chips are big, but then it's ridiculously fast (have you seen chatjimmy.ai?). Also they must be holding a bunch of patents.
Re:AMD acquires Taalas to boost inference performance by etc... by aenis on Friday August 07, 2026 @01:35AM (#49206243)
Its a cool demo, but its gpt-3.5 level stupid, or worse.

edit: Ok, I will self-apologize. Its apparently a 3B model. Mighty impressive for what it does.

Re:AMD acquires Taalas to boost inference performance by etc... by selcuka on Friday August 07, 2026 @02:05AM (#49206439)
It's a quantised 8B model (Llama 3.1 8B to be exact).

[1] https://taalas.com/the-path-to-ubiquitous-ai/

Re:AMD acquires Taalas to boost inference performance by etc... by teiferer on Friday August 07, 2026 @11:02AM (#49211532)
How time flies. Just 3.5 years ago, gpt-3.5 was touted as almost AGI, we're all going to be replaced by machines and worst case they will kill us all. And here we are, not much later, and it serves as the benchmark for "stupid"..
Re:AMD acquires Taalas to boost inference performance by etc... by aenis on Saturday August 08, 2026 @02:05PM (#49224256)
Yup.

Where I work we invited a bunch of people circa May 2023: a few top tier academics, a few government and NGO officials in charge of our industry, and a few startup founders. We are a big company, so people were kind enough to come and give speeches - and discuss.

This was a roundtable on what's going to happen. You could play some of the speeches verbatim today and they would not feel out of place. And that is telling. We had a Stanford professor saying that gpt-3.5 can do everything he can - just better, and he feels his profession is on borrowed time. We had a government guy saying that entire swaths of jobs will be displaced before the year ends. And so on.

The interesting thing is, a lot of people believed it then - and a lot of people believe it now. I wonder if we will have the same deja vu in, say, 2029. No, for sure not. It's going to be done and dusted for human thinking by end of this calendar year.

Re:AMD acquires Taalas to boost inference performance by etc... by mdp2021 on Sunday August 09, 2026 @07:30AM (#49230476)
> gpt-3.5 was touted as almost AGI

If you have the names, so we can record them in the History of Laughing Stocks...

Also remember maybe all those who shouted "that is really, precisely unintelligent".

Incidentally: also Sam Altman, in an interview with Lex Fridman, said "that is not proper intelligence but currently we do not know how to get there" - if very Altman refused to call it AGI...

Re:AMD acquires Taalas to boost inference performance by etc... by deaton on Friday August 07, 2026 @04:15PM (#49215679)
Sure but the first step to having something that is physically small, small enough to cram into an iPhone, is to have something that, at first, isn't.
Re:AMD acquires Taalas to boost inference performance by etc... by adgjlsfhk1 on Thursday August 06, 2026 @06:12PM (#49203332)
I don't think this works out from a cost/silicon perspective. Small models already run pretty well in software (since the weights fit in cache) and big models require silicon area proportional to the size of weights. On a mobile device putting a chip like this is competing directly in BOM and power against a whole lot more l3 cache, and the l3 cache makes everything faster
Re:AMD acquires Taalas to boost inference performance by etc... by dboreham on Thursday August 06, 2026 @08:12PM (#49204401)
Works great from a press release perspective though.
Re:AMD acquires Taalas to boost inference performance by etc... by teaearlgraycold on Thursday August 06, 2026 @06:36PM (#49203581)
My question is what changes about LLM use cases when you’re getting 1000 tok/s? Models in silicon might dramatically change how we think about them.
Re:AMD acquires Taalas to boost inference performance by etc... by HDBaseT on Thursday August 06, 2026 @08:04PM (#49204345)
In the case on on-device/self-hosted LLMs. You ask your agent to implement xyz feature 10 times and use a model to compare the outputs and combine the best results.

Raw intelligence becomes slightly less important when you can iterate and improve automatically. You can still claim it was "one shot" even when 30 different implementations were made then combined.

Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @01:20AM (#49206147)
Problem is, there exists no judge model that will really pick the same winner that you would.
Re:AMD acquires Taalas to boost inference performance by etc... by in_a_society on Thursday August 06, 2026 @07:22PM (#49203980)
The best way I can explain it is that it's the same feeling when I upgraded from 56k dialup to cable broadband.
Re:AMD acquires Taalas to boost inference performance by etc... by RussianCow on Thursday August 06, 2026 @06:43PM (#49203651)
That likely isn't as relevant for on-device iPhone usage as it is for Real Work™. I won't notice the difference between 50tps and 1000tps when asking Siri a question.
Re:AMD acquires Taalas to boost inference performance by etc... by spijdar on Thursday August 06, 2026 @07:11PM (#49203898)
I don't know. As others have said, the Taalas chip wasn't small, or particularly low power, so it's hard to "imagine" what that tech in an cell phone chip might look like.

But if the basic premise of "good enough LLM at insane throughput" holds, I think it could qualitatively change local uses of LLMs. At a certain speed point, you're able to move from request -> response to a cascade of tool calling and "subagents", which could allow a small model to be much more useful, if provided with a lot of local data and tool calls.

That said, this is assuming you could stuff a "good enough" model into a phone with Taalas-like technology. The Taalas tech demo was an 8B parameter model and required hundreds of watts (IIRC) to run. The efficiency was good given the speed (as I understand), but it's not clear at all that the approach scales small enough to be a sensible coprocessor on an iPhone or whatever.

Re:AMD acquires Taalas to boost inference performance by etc... by intrasight on Thursday August 06, 2026 @08:23PM (#49204465)
Box that plugs into my desktop would be fine. Or perhaps in SSF form factor.
Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @01:45AM (#49206295)
> At a certain speed point, you're able to move from request -> response to a cascade of tool calling and "subagents"

That also needs server class hardware though. A phone won’t happily service the insane amount of IO, compute, and network that this cascade would require.

Re:AMD acquires Taalas to boost inference performance by etc... by retatop on Thursday August 06, 2026 @07:20PM (#49203964)
But wouldn't higher tps allow for more reasoning or other hidden processes, potententially making a smarter model?
Re:AMD acquires Taalas to boost inference performance by etc... by dabbz on Thursday August 06, 2026 @07:58PM (#49204300)
This is my thought as well. Models have to be intentional about which tokens they burn because there's a real lag time. If you can just fork out 10 different reasoning sessions at once with no regard for token waste/lag, you can compensate a smaller model with just doing more at once with it. No idea if this is reasonably true though.
Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @01:35AM (#49206240)
I think that only works if you have checkpoints where all that reasoning can be checked against reality. Otherwise you get an army of armchair experts. LLMs are hilariously bad at home improvement advice btw, where reasoning alone won’t get you far.
Re:AMD acquires Taalas to boost inference performance by etc... by nvme0n1p1 on Thursday August 06, 2026 @07:22PM (#49203973)
That order of magnitude could be the difference between "the users wants me to open the notes app, let's open it" and "I've scanned all your notes before you could blink and found what you're looking for".
Re:AMD acquires Taalas to boost inference performance by etc... by p1esk on Thursday August 06, 2026 @07:39PM (#49204141)
If Siri is using a 3T model in high reasoning mode to answer your question you will.
Re:AMD acquires Taalas to boost inference performance by etc... by QuiDortDine on Thursday August 06, 2026 @08:24PM (#49204468)
Did you use chatjimmy? It's somewhat terrifying to use when you think of the potential results with a better model.

Ok, real life example: I now spend most of my time, as a developer, waiting for the agent to do its thing (after careful prompting, I'm also thinking about work stuff, don't worry I'm not useless). What if it gave back the same excellent results, but instantaneously? Why, then, I certainly would become the bottleneck. So, quite possibly, my last work task would be to plug this agent directly into the ticket system where the domain experts input their feature requests. Maybe we still need 1 developer out of 100, to coordinate releases and all that (ok, say 1 out of 10).

But that's not taking things far enough: why do we need these domain experts at all? Our pitch is clear, and all software-enabled, though it took years to develop. We can just have the clients express their concerns to the AI, directly or indirectly. Have multiple lighting-fast agents with different roles (refactoring agent, new features agent, debugger agent, domain expert agent, etc.). So we fire everyone, maybe keep 1 product owner / devops to keep the trolls out. The cost is still probably 100 times less than it used to be (beyond the initial cost of acquisition of the magic machine or whatever).

But one of these clients, surely, will realize that these 10 years of manual and slowly-automated development can now be emulated in very, very little time. Why not just, say, take screenshots of the entire app and feed them into the magic machine? Why, this way, they could have the service for a tenth of the yearly cost, forever!

And then the economy implodes.

I'm not saying it's THE most likely version of things, I'm saying that at a certain level, quantity (or rather, speed) is a quality all its own. And this new quality might change the world. Let's hope it's for the better!

Re:AMD acquires Taalas to boost inference performance by etc... by pastel8739 on Friday August 07, 2026 @12:02AM (#49205783)
This is the same pitch that people make about AI today. Speed isn’t the differentiator, quality is
Re:AMD acquires Taalas to boost inference performance by etc... by Certhas on Friday August 07, 2026 @01:35AM (#49206241)
So for every work produced by AI have ten separate agents review it thoroughly.
Re:AMD acquires Taalas to boost inference performance by etc... by sroerick on Friday August 07, 2026 @02:54AM (#49206813)
They are both the differentiator.

AI previously provided speed but not quality. As soon as quality reached an acceptable threshold, the speed became the reigning factor.

In my opinion the quality is still much lower, but speed means the cost is significantly lower also.

Re:AMD acquires Taalas to boost inference performance by etc... by TeMPOraL on Friday August 07, 2026 @04:11AM (#49207322)
AI is already fast enough that human is a bottleneck. Hell, typing speed became a bottleneck like it was never before.

I mean, if an agent can do half-decent work in less time than it takes the user to prompt them (and "user" in this context is a fast touch-typist like most programmers are), it's obvious it's not the agent that's the bottleneck anymore.

Re:AMD acquires Taalas to boost inference performance by etc... by tripzilch on Friday August 07, 2026 @07:04AM (#49208568)
Because finishing someone else's (or something else's) "half decent work" to the point of "actually decent" becomes the bottleneck.

This has always been the case for human project management, and LLMs just aren't at that level yet.

It's more like everyone is speed running to how fast they can convince others that "half decent" is good enough. And for sure, newer models of LLM seem to be getting better at that.

Re:AMD acquires Taalas to boost inference performance by etc... by TeMPOraL on Friday August 07, 2026 @05:59PM (#49216724)
> It's more like everyone is speed running to how fast they can convince others that "half decent" is good enough.

But that's what Agile is all about, isn't it? We've been speedrunning delivering increasingly smelly shit at increased velocity ever since SaaS became a thing, because ubiquitous Internet access is what allowed our industry to adopt the "lob feces over the fence for users to deal with" release model.

AI does speed that up, true (though since the market - and management - didn't catch up with it yet, we have a brief moment where we can use AI to increase quality while keeping usual delivery rate.)

Re:AMD acquires Taalas to boost inference performance by etc... by tiborsaas on Friday August 07, 2026 @06:44AM (#49208412)
Speed will be one of the killer features once you get closer to instant speeds of 300ms. Just remember what changes were made possible simply by upgrading from ADSL to broadband.

If inference speed goes up, I can launch the same query 5 times, evaluate the best result and proceed from there. Of course, evaluation is also instant, so in seconds I can get a near perfect solution. Or maybe 10 and I can pick what I like the best.

Re:AMD acquires Taalas to boost inference performance by etc... by xur17 on Thursday August 06, 2026 @09:14PM (#49204762)
I'm not sure inference speed is always the slowest thing for me right now. The agent is running tests, loading webpages, etc, which all take time. I don't know if a fast agent would speed things up in all cases.

That said, it obviously depends on the project.

Re:AMD acquires Taalas to boost inference performance by etc... by jodrellblank on Thursday August 06, 2026 @09:32PM (#49204884)
> "The agent is running tests, loading webpages, etc, which all take time"

A frustrating vision of the future would be when we've been asking for faster loading lighter web pages for years and then companies start caring about it and improving it not for us humans but for LLMs.

Re:AMD acquires Taalas to boost inference performance by etc... by evilduck on Thursday August 06, 2026 @10:32PM (#49205309)
It's already kind of that way with MCP servers popping up everywhere. The JIRA MCP server is like a couple orders of magnitude faster to work with than the website itself.
Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @01:10AM (#49206093)
That’s their API with extra steps, or am I missing something? That was always faster.
Re:AMD acquires Taalas to boost inference performance by etc... by evilduck on Saturday August 08, 2026 @11:07AM (#49222554)
The extra steps with AI are a better and faster user experience than their website.
Re:AMD acquires Taalas to boost inference performance by etc... by andersonpico on Thursday August 06, 2026 @10:56PM (#49205435)
They finally cared about clear requirements and documentation when that meant getting rid of devs.
Re:AMD acquires Taalas to boost inference performance by etc... by layla5alive on Thursday August 06, 2026 @11:35PM (#49205647)
That happened at corpo work for each of: * Build times * CI latency * Developer tooling * Documentation * Modularity
Re:AMD acquires Taalas to boost inference performance by etc... by bdangubic on Thursday August 06, 2026 @10:27PM (#49205279)
> I now spend most of my time, as a developer, waiting for the agent to do its thing (after careful prompting, I'm also thinking about work stuff, don't worry I'm not useless).

you need to launch 10-15 more terminals, who is waiting these days? :)

Re:AMD acquires Taalas to boost inference performance by etc... by QuiDortDine on Friday August 07, 2026 @09:00AM (#49209755)
You sound like my boss! I'm not really into the whole "burnout" thing though.
Re:AMD acquires Taalas to boost inference performance by etc... by bdangubic on Friday August 07, 2026 @08:50PM (#49217856)
how can you get burned out just watching the work being done for you?? :)
Re:AMD acquires Taalas to boost inference performance by etc... by wsintra2022 on Thursday August 06, 2026 @08:49PM (#49204623)
I think this reads like Ray Kurzwheil (sorry not able to spell that off top of my head, that bloke who wrote that book about the future) .. But yeah very dystopian and totally realistic. Not if but when..
Re:AMD acquires Taalas to boost inference performance by etc... by QuiDortDine on Thursday August 06, 2026 @08:53PM (#49204644)
I LOVE Kurzwheil! Thank you for the compliment, I'm very far from having his writing skills. But yes sci-fi is looking more and more like, well, sci.
Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @01:15AM (#49206113)
Errors compound, and making 1000 wrong decisions per hour, will not result in something useful. Maybe you‘ve tried setting up guardrails for good design or architecture at some point? I think it’s simply not possible to do that.

It would certainly be an accelerator for people who know exactly what they want. And it would remove multi tasking, which I‘d appreciate.

Re:AMD acquires Taalas to boost inference performance by etc... by Ericson2314 on Friday August 07, 2026 @03:50AM (#49207184)
If your task has incremental rewards/feedback, you can push the "intelligence rate" simply by sampling the reward function faster. That's not fake, even if it not a substitute either.

This is the "dumber but honest person that works harder" phenomenon, vs "lazy genius".

Re:AMD acquires Taalas to boost inference performance by etc... by gf000 on Friday August 07, 2026 @04:00AM (#49207256)
That's a good way to put it, but still my experience is that worse code bases are non-linearly harder to maintain and improve in the future, software tends to break down without a good enough base.

Sure, in the future full rewrites and stuff like that will be just another "throw money at it" problem, but fundamentally software can get arbitrary complex and we barely know how to write large, maintainable code bases.

Nonetheless, I think testing (and maybe proofs) will have its long-awaited time to shine, as being the "reward function".

Re:AMD acquires Taalas to boost inference performance by etc... by Ericson2314 on Friday August 07, 2026 @01:19PM (#49213530)
I totally agree with you on the first bit, but I also think that I am way better at deciding on how to refactor code bases than the LLM is.

Right now, I put models in low thinking mode during my refactors and hate waiting. I would much rather have a faster model that that maybe was slightly stupider, and I would wait far less long between prompts where it needs my valuable input.

Models that are dumb, but humble and fast, can be fine.

Re:AMD acquires Taalas to boost inference performance by etc... by momojo on Friday August 07, 2026 @11:55AM (#49212372)
I don't have a great answer but you pose a great question.

Obviously a CTO is not going to walk away from the technology just because it's not good enough. That much more incentive for someone to create a powerful enough harness that can direct that power safely and productively. Like a nuclear core, we'll need to come up with the graphite rods and water tank. And if tokens are essentially free, why not, for every million tokens, spend 10x tokens on code review, testing, etc?

Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @03:23PM (#49215133)
I do spend 5x more tokens on planning and reviewing, than for implementation. But architecture is still nothing I can delegate.
Re:AMD acquires Taalas to boost inference performance by etc... by visarga on Friday August 07, 2026 @01:38AM (#49206258)
AI helps you but also your competition, and gets factored in by investors while customers can use it to find better deals. The whole market is different even if a company did nothing.

Whatever you can cheaply do with AI is not a moat, if there is profit in there there will be quick imitation and competition will eat away those profits.

Models can be replaced easily, harnesses & AI tools too. And if cloud inference gets too expensive there are local models keeping the cloud prices hard capped.

Probably AI won't make anyone very rich.

Re:AMD acquires Taalas to boost inference performance by etc... by IOT_Apprentice on Friday August 07, 2026 @01:51AM (#49206340)
I tried it. I asked where Bruce Lee was born. It stated he was born in Hong Kong. I challenged it and it went further naming a hospital there. I stated he was born in San Francisco and it apologized and then said his father was a missionary traveling in America, which was also wrong. Bruce’s father was a famous Cantonese Opera singer and actor.

This model had zero information right, while being fast in responding.

Unacceptable.

Re:AMD acquires Taalas to boost inference performance by etc... by selcuka on Friday August 07, 2026 @02:42AM (#49206721)
It gave the correct answers to both questions for me:

> Bruce Lee was born in San Francisco, California, USA on November 27, 1940.

> Bruce Lee's father was a Chinese opera singer

That being said, this is not a good test. It is a language model (a very small one), not an encyclopedia.

ChatJimmy interface is just a tech demo. Without tool calling functionality we can't expect it to be factually correct.

Re:AMD acquires Taalas to boost inference performance by etc... by logicallee on Friday August 07, 2026 @04:14AM (#49207345)
if it's baked into silicon how can you two get different answers?
Re:AMD acquires Taalas to boost inference performance by etc... by v9v on Friday August 07, 2026 @04:48AM (#49207593)
It still works the same way other LLMs do, by outputting the probability distribution over the possible completions (The weather is ... (sunny (50%), cloudy (50%))). Then the next token is sampled from this probability distribution (in our example the next word could be "sunny" or "cloudy" equally likely), which can result in different outputs every run.
Re:AMD acquires Taalas to boost inference performance by etc... by logicallee on Friday August 07, 2026 @06:48AM (#49208432)
Could the model or algorithm be changed to make it deterministic somehow? It could help a lot if there were reproduceable outputs from deterministic baked-in silicon.
Re:AMD acquires Taalas to boost inference performance by etc... by Tuna-Fish on Friday August 07, 2026 @09:03AM (#49209791)
You can make any LLM deterministic by dropping the temperature hyperparameter to zero.

This will generally make them suck, though, a little bit of randomness is necessary for proper function.

Re:AMD acquires Taalas to boost inference performance by etc... by fwip on Friday August 07, 2026 @10:04AM (#49210633)
You can also use a fixed seed for your prng. A hash of the input text (up to the current turn) should do.
Re:AMD acquires Taalas to boost inference performance by etc... by fph on Friday August 07, 2026 @04:31PM (#49215854)
But since it's so fast you can just ask it 100 times where Bruce Lee was born, and statistically you'll get the correct answer. We could call it "mixture of idiots". /s
Re:AMD acquires Taalas to boost inference performance by etc... by TeMPOraL on Friday August 07, 2026 @04:29AM (#49207433)
That's not what speed is useful for.

I just pasted your comment and its whole inheritance chain to it, started my comment, and asked to generate a total of 9 completions, 3 from each of {current & next word, current paragraph, current paragraph + rewrite the entire paragraph}.

Half of the answers were perfectly good (ironically, not the "next word" ones!), but the important bit, they came back near-instantly ("Generated in 0.024s - 14,163 tok/s", the page says). Slightly more powerful model while keeping this under a second, and this could easily become a qualitatively different form of autocomplete/text suggestion. Running in the background every couple keystrokes, or every time user stops typing for more than 500ms.

Re:AMD acquires Taalas to boost inference performance by etc... by logicallee on Friday August 07, 2026 @06:44AM (#49208408)
>That's not what speed is useful for.

>I just pasted your comment and its whole inheritance chain to it,

Good idea. Only problem is it doesn't work. I just did the same thing with exactly this prompt:

>did the user IOT_Apprentice participate in the thread below and if, number and quote all of their comments. Only just number and quote the comments or write "Did not participate", do not add any commentary. Quote any comments by this user verbatim, exactly as input. Thread:

followed by pasting the thread[1]

And received the answer "IOT_Apprentice did not participate in the thread."[2] in 0.001s, even though they have literally the last comment in my quote and it's clearly legible.

It's particularly insidious because the understanding and thinking that is required to follow my requested answer format exactly is substantial - so based on the fact that it gets the format right and clearly understood the assignment, I would be inclined to believe that it would also be correct!

So to use your example, it's not just autocomplete, it's autocomplete that confidently returns "No matching results" in 0.001 seconds, even though there is a search term matching what you put in, right in the prompt itself that was sent to it. That is much worse than useless.

[1] prompt: https://ibb.co/CKVmRvtd

[2] result: https://ibb.co/BKdRKmyD

Re:AMD acquires Taalas to boost inference performance by etc... by tliltocatl on Friday August 07, 2026 @05:00AM (#49207695)
Using LLMs for information retrieval is the most stupid thing one can do. Especially when old methods work much better.
Re:AMD acquires Taalas to boost inference performance by etc... by LarsDu88 on Friday August 07, 2026 @12:43AM (#49205973)
Massive economic simulations with thousands if not millions of agents to front run the global economy and stock market.

Fully interactive realtime NPCs in videogames at scale.

Recommender systems that simulate individual consumers.

Crazy shit

Re:AMD acquires Taalas to boost inference performance by etc... by manmal on Friday August 07, 2026 @01:26AM (#49206188)
About your first example, isn’t the butterfly effect preventing this from being useful? One agent in your simulation decides to sell, and starts an avalanche, that won’t happen in reality?
Re:AMD acquires Taalas to boost inference performance by etc... by bostik on Friday August 07, 2026 @02:28AM (#49206618)
When you run tens of thousands of simulations for complex economic models, you actually do want to see the extreme outliers too. I can't recall who said it, but in finance the interconnected incentives make so-called Black Swan events much more likely and frequent than models or theories can comfortably account for.

In a way... when it's finance, they should be maybe called Gray'ish Swans?

Re:AMD acquires Taalas to boost inference performance by etc... by LarsDu88 on Saturday August 08, 2026 @03:30AM (#49219644)
Run the sim many times... faster than it can run on actual humans and compute a probability density for specific events.

Better yet use it to dimulate counterfactual phenomena like market manipulations ypu intend to enact...

Re:AMD acquires Taalas to boost inference performance by etc... by TeMPOraL on Friday August 07, 2026 @04:08AM (#49207305)
It's pretty clear if you see what's happening on current phones.

Autocorrect that works. Reply suggestions that almost work, just need to be tad more accurate (probably more of a data access issue than model) and a tad faster to look completely seamless. Screenshots with automated text detection and OCR and automatic interpretation (different suggested actions for when something on the picture looks like a web link, phone number, postal address, e-mail, or QR code, or an event poster). That's just a fraction of things I saw showing up on my Samsung phone over the last 6 months.

For over a year now, you could get a much better autocorrect and spell/grammar check, and a translator all in one, if you just pasted your text to a frontier model and asked it to check for errors or translate into target language. Now imagine being able to go through a round of such checks in a 1/100 of a second. You could have this running every keystroke, and suddenly the inline autocorrect/checks would not suck anymore.

Auto-linkifying that can correct for typos and doesn't need careful regex tuning because it understands from context what is meant to be a link or not. That's just one of many obvious things possible once you get local models running fast enough. Tip of an iceberg, and the first step to imagining all the other potential uses is to let go of the two mistaken beliefs people hold on to:

1. That LLMs are about written language. They're not; ever since "multimodal models" became a thing, tokenization extended to visual and audio space, and now textual and visual and aural inputs are all just regular, first-class tokens.

2. That chatting with the models is the only optimal way for end users to interact with AI. That's just artificially limiting yourself to the space of chat-based UI.

Re:AMD acquires Taalas to boost inference performance by etc... by bastawhiz on Thursday August 06, 2026 @06:39PM (#49203604)
The weights might fit in cache, if you're using a small model. If you wanted to have a 20B+ parameter model, that's just going in RAM. You could put more RAM in the device and pay the perf cost or have a dedicated chip. Most devices already have a dedicated chip, this just changes which silicon you're spending the money on.
Re:AMD acquires Taalas to boost inference performance by etc... by wmf on Thursday August 06, 2026 @08:07PM (#49204361)
That math doesn't really work.

8B model (FP4) = 4 GB DRAM = 32 Gb DRAM = 80 mm2

8B model (Taalas) = 4 GB ROM = ~800 mm2

Re:AMD acquires Taalas to boost inference performance by etc... by trebligdivad on Thursday August 06, 2026 @08:46PM (#49204604)
What, even if it means you can run models without relying on the currently backlogged DRAM production?
Re:AMD acquires Taalas to boost inference performance by etc... by adgjlsfhk1 on Thursday August 06, 2026 @10:18PM (#49205227)
The size of model we're talking about running doesn't need much if any dram.
Re:AMD acquires Taalas to boost inference performance by etc... by trollbridge on Friday August 07, 2026 @03:16AM (#49206952)
The chatjimmy demo is using a model that needs 6-18GB of VRAM. That's not exactly trivial.

I could see it being feasible to get a Qwen-3.6-27b type of model done on something like this. Qwen-3.6-27b at 18tok/s would be a game changer.

Re:AMD acquires Taalas to boost inference performance by etc... by adgjlsfhk1 on Friday August 07, 2026 @08:34AM (#49209443)
right, but that's a reticle size chip. to put something in a phone it has to be ~10-30x smaller
Re:AMD acquires Taalas to boost inference performance by etc... by makeitdouble on Thursday August 06, 2026 @07:29PM (#49204056)
Slightly besides your point, but it's interesting how many here naturally ponder about how the current winner could or "should" keep winning, instead of how another company could become a competitor by doing the more clever thing the incumbent isn't thinking about.
Re:AMD acquires Taalas to boost inference performance by etc... by krisoft on Thursday August 06, 2026 @08:20PM (#49204443)
It is not a “should”. At least not in the “we wish it were so” sense.

It is more that there are multiple reasons why this idea (burning an LLM into silicone and deploying it into a device in people’s pockets) requires huge piles of cash and the kind of engineering chops only a few company posesses.

Of course i would like it if a small upstart would do this, but it doesn’t seem likely as a posibility. They won’t have the funds to fab the IC. They won’t have the funds to train and validate the model before burning it into silicone. They can’t absorb the risk of the first tape out going wrong. They can’t absorb the risk of the model being faulty in some subtle way. They don’t have a device to integrate the IC into. They won’t have the funds to develop one. If they somehow would make a device they don’t have the marketing and sales channels built out to get the device into people’s hands in sufficient numbers to justify the development cost.

Basically this idea feels ruinously expensive. Apple has deep pockets, they already have working well-regarded phones, and an ethos of privacy preserving innovation. This is why this idea feels well suited for them and not many others.

Do i want the winners to keep winning? No. But not many others can pay for a moonshot crossed with a manhattan project. They just can’t.

Re:AMD acquires Taalas to boost inference performance by etc... by ricksunny on Friday August 07, 2026 @02:33PM (#49214565)
Yes, it's an interesting register (sorry for the claudism; blame lesswrong-weighted training) for the use of the word 'should'. I agree with your assessment and it is rarely articulated. Sometimes I think that the HN set is abused by big tech both from above on the employer side and the consumer usage side (all the T&C's, VC incentives and M&A taking away once-good-things). So they adopt the only sliver of agency-salving language available, like 'big company that I have no scope over should X'.
Re:AMD acquires Taalas to boost inference performance by etc... by makeitdouble on Saturday August 08, 2026 @12:22AM (#49218868)
Good point. IMHO we're thinking of too much in single entities doing everything.

Right now it's kinda the world we live in, with Apple or Google doing the total vertical integration from chip design to retail shops, but it doesn't have to be that way.

It could be done the traditional way with for instance a joint venture receiving funds and expertise from several players in each of the field and collaborating with external companies to get to the final package.

Re:AMD acquires Taalas to boost inference performance by etc... by bsaul on Thursday August 06, 2026 @05:59PM (#49203188)
That's actually a really good point... There's currently zero incentive to buying more hardware, and that's one very good reason do have a new one.
Re:AMD acquires Taalas to boost inference performance by etc... by sebular on Thursday August 06, 2026 @07:13PM (#49203910)
But this is already happening with iPhones. Apple is touting on-device AI and only the latest phones offer the full capabilities. Newer phones will be able to run better models, so the incentive is there as soon as someone makes the killer app that only makes sense when the model is running locally on your phone.
Re:AMD acquires Taalas to boost inference performance by etc... by amelius on Friday August 07, 2026 @04:55AM (#49207654)
> as soon as someone makes the killer app that only makes sense when the model is running locally on your phone.

I expect this to be around the time when we're finally ready to travel to Mars.

Re:AMD acquires Taalas to boost inference performance by etc... by superb_dev on Thursday August 06, 2026 @06:07PM (#49203274)
From what I remember, these chips are not mobile size yet
Re:AMD acquires Taalas to boost inference performance by etc... by bradfa on Thursday August 06, 2026 @06:11PM (#49203321)
A small model would be. I think that’s more the point. It’s definitely not SOTA but it’s fast and energy efficient and local.
Re:AMD acquires Taalas to boost inference performance by etc... by mdp2021 on Thursday August 06, 2026 @06:27PM (#49203496)
> A small model would be [mobile size]

A ~30mm side for the HC1 tech for an 8b model (still unclear the planned HC2)?

Re:AMD acquires Taalas to boost inference performance by etc... by teaearlgraycold on Thursday August 06, 2026 @06:37PM (#49203593)
Is that analogue or are they baking floating points into the silicon?
Re:AMD acquires Taalas to boost inference performance by etc... by AlotOfReading on Thursday August 06, 2026 @08:20PM (#49204444)
It's entirely possible they're using something like block floating point, where most of the hardware is simply fixed point. AMD's NPU does this, for example.
Re:AMD acquires Taalas to boost inference performance by etc... by wmf on Thursday August 06, 2026 @06:31PM (#49203526)
Nope, a small model would be larger than the whole iPhone SoC.
Re:AMD acquires Taalas to boost inference performance by etc... by whatsThisBtn4 on Thursday August 06, 2026 @06:34PM (#49203558)
Apple is somewhere between fashion company and second rate tech company.

They could have 9 year old AI and still post profits.

Not sure if it's my pixel or android, but I made a randos jaw drop with what the crappy AI on android can do.

When are we getting android OpenClaw?

Re:AMD acquires Taalas to boost inference performance by etc... by freekh on Friday August 07, 2026 @02:22AM (#49206577)
It would be cool if the future was a standard fairphone like module system where you could replace the model chip when you felt like it without having to shell out 1-2k $$$s for a new phone
Re:AMD acquires Taalas to boost inference performance by etc... by dzhiurgis on Friday August 07, 2026 @06:08AM (#49208189)
Its wild but if chip is something like $30 and provides frontier intelligence then just throwing them away every 3 months isn't that big of a deal when a lot of us pay $50 to $150 to $1.5k per month on AI tools.

I don't think it needs to be on phone per-se. It can keep chugging in cloud - plenty of people use cheaper older models.

And I suspect the growth will slow eventually making taalas interations slower.

Re:AMD acquires Taalas to boost inference performance by etc... by koiueo on Friday August 07, 2026 @08:16AM (#49209255)
> if you could burn a gemma4 class model into an iphone

... you would still have a mediocre phone with half-assed barely working features driven by locked down proprietary software