darkpicnic

If payloads to LLMs are being passed around to various nodes, even trusted ones (like friends and family), it gets awkward if you send something very personal. Think sending a medical question to medgemma:27b.

Does Mesh LLM encrypt the payload between nodes? Is it possible to read requests from other users?

Good point. I know cocompute is working on splitting, but it’s not there yet; I was referring to the round-robin delegation within a trusted pool. Mesh LLM looks great too!

cocompute.ai is already doing this really well.

Just do what I did: ignore your orthodontist and wear them only at night, smashing them into your mouth like some kind of idiotic brute. 4 years later, great teeth!

LLMs won’t lead to AGI. Almost by definition, they can’t. The thought experiment I use constantly to explain this:

Train an LLM on all human knowledge up to 1905 and see if it comes up with General Relativity. It won’t.

We’ll need additional breakthroughs in AI.

I created an open source tool to help apps stay near the Dunbar Number: https://highlyprobable.io/articles/ten-cubed. I think the concept of social networks is interesting, but the ultimate unbounded result is a disaster.

Edit (missing link to github repo): https://github.com/darkpicnic/ten_cubed

I've always been confused by this First Amendment argument with regards to TikTok: they're an organization that has been tied directly with an adversarial foreign state. How is this a rational take? Using this logic, Russia should be allowed to foment unrest through fake hate groups on Facebook (which they've done).

People should familiarize themselves with Gresham's Law: bad actors will always beat good actors if bad actors suffer no penalty. If bad actors leverage the rights and freedoms of a democracy to perform attacks without repercussion, we're toast.

"Silence" is a problematic term. For me, that word encompasses: squeaky chairs, typing on a loud keyboard, moving objects around on my table, etc. In a perfect world, Whisper —like a human— can easily distinguish a human voice from the din of my office, and only try and transcribe my voice.

Does anyone have solutions for clearing out "silence" from an audio file that works off something a bit more accurate than just "<= decibel x"?

Edited for grammar.

Does anyone know if this new model handles silence better? I was trying to use whisper for transcribing bursts of talking amid large spans of silence, but the frequency of hallucinations was too high.

I just wrote a script with Hazel to automatically transcribe my voice notes to txt. It handles punctuation extremely well. What a wonderful contribution!

Simply put: your state exists on each client and the mechanism to reconcile that state across clients is not mission critical. Almost all apps currently are built to get their state from a centralized, remote location. This is easy to build but is fragile and not forgiving for loss of network connection.

CRDTs and local-first ideals means putting the client in charge of its state which leads to all these positive side effects: virtually instant UX interactions, privacy (your not sending data necessarily to a central server, and even if you are it could just be opaque, encrypted blobs that are proxied), network-agnostic syncing (email, bluetooth, internet, wifi, etc) and no fears of a service completely going out of business and losing your data.

You're describing one of my favorite mental models: https://fs.blog/2020/03/chestertons-fence/

I don't think this analogy works. I think it is more akin to police opening a folder and seeing paper evidence, but having no idea who put the paper there, when it was last opened/modified and unable to determine if the evidence is legitimate.

For me, this story isn't about fear that police could leverage the bugs to manipulate a case. It's about the constant fear that laymen rely on unverified "experts" to put people behind bars for years.

I'm glad to see this article is eliciting in others the same reaction I had when reading it. I'm a huge fan of Linear and use it for our company, but this article just has so much hand-waving going on it's staggering. Where is a single example? They claim that user stories are outdated, inefficient, not valuable and yet show no alternative to the seriously difficult problem of engineering tasks missing context and purpose, especially after a certain amount of time has passed. I can't count the number of times I've fired off a one-line task thinking "This is fine. I'll remember what I need to do when I get to it" only to, after a few weeks, go "WTF?".

The part about writing your own tasks is also strange. So my coworker finds an issue and instead of just writing the task out with context, explanation and direction, he has to... explain it to me in some medium... then I go do it? Really?..

I feel like this article was written as some kind of SEO "let's just get people here looking at our product" kind of thing. I can't believe this was written by someone who actually writes software.

(edited for typos)

Hilarious. Thanks for sharing!

Man, this is why self-driving cars can’t come soon enough. Everyone else’s replies to this already sort of answer your question, but for me this hints at the bigger issue: people don’t take driving seriously. My counter is: why do you need to be looking at your phone in a car? What text is so important that you can’t pull over and read it? Why give up the situational awareness that is absolutely required to safely operate a machine that can kill people?

Life is about trade offs and constant cost/benefit analysis. How is reading/responding to a text message slightly sooner worth the decrease in situational awareness and possible accident involving a 2 ton vehicle?

I think we have normalized the dangers of driving a vehicle to the point where we sort of just shrug at the monumental number of vehicular deaths. I’m confident that when my kid is an adult, he’ll look at us with astonishment when we say we used to drive vehicles around, poorly trained, staring at phones, half-drunk, kind of paying attention sometimes, a bit sleepy and it was not only legal but _normal_. It’ll be like us hearing about how our great-grandparents had a 2 year old work dangerous farm equipment alone. You think “How the hell did anyone survive?”

Yep, I was just highlighting the fact that most articles about Level 2 or, in general, < Level 4, are written with a concern for situational awareness. In my experience, it was the opposite: it improved it.

It's interesting reading articles about Level 2 and how it can adversely affect driver attention. I was concerned when I started driving a Tesla for the same reasons. Would I grow complacent? Stop paying attention?

The opposite happened. I'm more focused on the road since I can relax and not multi-task. On long road trips, I'm not feeling that ache in the knee or the tension in the shoulders/back from constantly keeping the car aligned in the lane. In fact, I wish Tesla would just introduce a touch interface into the wheel so it knew your hands were on it, but not require constantly resisting the wheel to trigger the sensor.

The conclusion I've come to: Level 2 can make good drivers safer and make bad drivers more dangerous. I don't look at my phone when I'm driving. I don't text at red lights. I don't constantly fiddle with the screen. If you do these things, you're a dangerous driver. If Level 2 increases this because you feel a false sense of safety, it'll make you more dangerous.

People just need to take driving a 2 ton heap of metal 70mph seriously and we'd all be much safer.

I wish more blog posts were like this. Just really useful, real-world information packaged as a set of bullet points. Bravo.