hgo

My experience is not the same. Opus 5.5 lets me work as much as I want and I can't deplete 20x.

To me, it sounds like the point of the article is that we're skipping the nuance and jumping straight to effectively declaring equality between AI use and slop, which is a bit sad in a couple of ways: a) effort is apparently so rare, that the distinction between effortful content creation with AI and opportunistic press-a-button "content" creation is too difficult. b) real pervasive concern about our future (rightfully?) motivates sweeping judgement against the whole creative space with any AI involved. c) concretely, its sad in itself that any arena of expression is overwhelmed with low effort.

On the other hand, by the very nature press-a-button content is so easy to make that it will naturally bury real content unless someone takes an active gate keeper role. (Every channel on Youtube I know has made in-depth complaints that this is not happening there.)

I hope we find a way around it, so that we can enjoy content and products that is made with the same amount of effort as before but with more powerful tools creating a better end result. Not to mention lower barrier to entry into creative spaces, giving us more perspectives and ideas expressed in a quality way.

I have to say that I'm very pleased with this version.

My prime anecdotal reason: I asked Opus 5.5 to make a sweeping change with a few Sonnet agents. It clarified the scope, we agreed and then it started. I saw some problems on the way and asked it. It's answer: This didn't go as planned. The Sonnet agents don't have the right judgement capacity for this, so they take shortcuts based on their limited scope X. I suggest we terminate them, roll back their changes and I can schedule an Opus agent to do it instead. It will be slower but done correctly.

There is a first time for everything.

Every interaction I've had with Opus 5.5 so far feels like talking to. An adult.

I saw the announcement video and I'm so relieved to hear actual honest language!

- Actually naming your inspiration as Apple

- Saying that thanks to machined body, the keyboard is actually slightly better. No overstatement, just an honest detail

- No: "This is our best laptop yet" (As if managing to not making it worse is something to be proud of)

- To the point, fast paced, clear communication

- Honestly stating that you're working hard on getting as good as "the gold standard, which of course is Apples track pad" and that you think you'll get there soon

- Clearly stating that the new memory standard is not magically your own invention somehow even though you're the first to use it

- Clearly stating the actual numbers of the battery in Wh and density AND also how many video minutes you get

- Clearly stating, not hiding but also not overstating that you started the company for the purpose of upgradeability

- Proving what you mean with examples before emphasising that "we really mean it when we say we have redesigned the computer from the ground up" (While absolutely fantastically letting the new motherboards upgrade last generation chassis!)

Result: I placed a pre-order, and kind of felt sad for this honest and clear language to apparently be rare.

Ah, seems like the right thing. To be more clear on what I'm looking for is this: the system using the LLM gateway would present an arbitrary user id. Let's say the system has thousands of end-users (completely managed by that system and not configured in the LLM proxy). The admin is interested in blocking end-users from using more than a certain allowed quota.

Hey, this looks super nice. I do like the 'compact' feel of this. Reminds me of Traefik. It seems very promising indeed!

One problem I have is that yes, LiteLLM key creation is easier than creating it directly at the providers and managing it there for team members and test environments, but if I had a way of generating keys via vault, it would be perfect and such a relief in many ways.

I see what I need on your roadmap, but miss integration with service where I can inspect and debug completion traffic, and I don't see if I would be able to track usage from individual end-users through a header.

Thank you and godspeed!

Cheerful intro do DIY combustion, milling, nozzles, simulation, machining.

Yes, I agree and I use LLM in writing myself. I raise it because it was eerie to me as a reader and I wonder if its a common thought. I wonder what other readers think on this matter.

Again, I appreciate the article very much and I'm glad the other comments are on the article's content.

Yes. Let's assume so. My point is the suspicion itself.

I like this article and it reads well, but I have to say, that to me it really reads as something written by an LLM. Probably under supervision by a human that knew what it should say.

I don't know if I mind.

Example. This paragraph, to me, has a eerily perfect rhythm. The ending sentence perfectly delivers the twist. Like, why would you write in perfect prose an argument piece in the science realm?

> Unlike Alice, who spent the year reading papers with a pencil in hand, scribbling notes in the margins, getting confused, re-reading, looking things up, and slowly assembling a working understanding of her corner of the field, Bob has been using an AI agent. When his supervisor sent him a paper to read, Bob asked the agent to summarize it. When he needed to understand a new statistical method, he asked the agent to explain it. When his Python code broke, the agent debugged it. When the agent's fix introduced a new bug, it debugged that too. When it came time to write the paper, the agent wrote it. Bob's weekly updates to his supervisor were indistinguishable from Alice's. The questions were similar. The progress was similar. The trajectory, from the outside, was identical.

In my mind, this "observation" (if I can call it that) may explain or at least relate to what other commenters bring:

> I don't know what to think. These blog articles are supposed to be a showcase of engineering expertise, but bragging about having AI vibecode a replacement for a critical part of your system that was questionably designed and costing as much as a fully-loaded FTE per year raises a lot of other questions.

https://news.ycombinator.com/item?id=47537229

> I shared the numbers internally and someone asked about the ROI. Production cost for jsonata-js in the previous month was about $25K - now it was 0. That conversation ended up being pretty short.

I'm obviously projecting from my own experience, but it echoes so clearly how power can be wielded without actual insight and an almost arrogantly: "OK, all very nice, but the ROI...?"

The article seems to come from a company with stellar engineering so maybe doesn't apply to this case. But, the tone I imagine from that comment still stands out. To me more, precisely because of the mature engineering.

Of course ROI is important and a company exists to build it. I'm extrapolating from something tiny and thinking of the Boeing culture shift: https://news.ycombinator.com/item?id=25677848

In short, why can't good engineering just be good engineering fostered with trust and then profits?

I really appreciate this post. Freely and humbly sharing real insights from an interesting project. I almost feel like I got a significant chunk of the reward for your investment into this project just by reading.

Thank you for sharing.

Oh, I didn't know github had free macOS CI runners. Maybe that would solve my dreadful upcoming issue that I'd have to update my mac to a version with glass to be able to build for the app store.

Remember hotornot.com? Soon we can muse at realornot.com

Can this be read as finally the financial incentives to join the AI silicone race has become too tempting. Finally the incentives to sell chips are definitely stronger than the cost of competing with your own licensees?

If I was an investor in an AI provider I would be quite worried.

1) Switching between LLM API:s is incredibly easy if you are not concerned with differences in personality. As the models get better, it is less important to pick the best one.

2) The products built to bundle the API with a user experience are difficult to build on a level that outclasses open source alternatives.

3) Building an understanding of the user to increase the product value over time and create stickiness is effective, but imho less effective over time as time passes and the user changes. For example, I suspect that these adaptations have a hard time to unlearn things that are no longer true. Learning about the user opaquely is less useful to the user and doing it overtly makes it easier to take the learnings and go. (Besides, it is probably not legal under the GDPR to not let the user export the learnings and take them to another provider.)

Taken together, the moat becomes quite shallow. I see why they aggressively ban any tools demonstrating when open alternatives are in fact better than their own walled gardens.

edit: readability.

If they had OpenAI Slack, maybe it would get better organized.

It's wonderful to see LLM's being used to increase the programming community's general quality level of work, as more things become worth doing.

Thanks, I think I understand roughly. Could it be used for for recognizing people? As in identifying what person is in what image?

I'm not confident in what I'm saying here, so please correct me if I'm wrong as I'd like to learn:

Human hearing isn't linear in terms of loudness. So a 3db increase in loudness sounds like "an increase", but the pressure is actually double. Hence, it makes sense to use db to describe loudness even in the context of perceived loudness to human-hearing.

This is similar to brightness. In photography, "stops" are used to measure brightness. One stop brighter is technically twice the light, but to the human eye, it just looks "somewhat brighter", as human brightness appreciation is logarithmic, just like "stops" and "db".

Thank you, I'm already paying for a lower-tier Kagi plan. Forgot about their AI offering.

Excellent, thank you

I _need_ to tinytapout! Don't know what, don't know how, but the sense of need is tickling! I feel like twelve again in front of a 286 without a case.

Would it be possible for the allocator/GC to know what allocations are made within a request and make a generation for specifically for it? Allocations too big to fit would be made like usual