Until it says it's done. One of the more surprising advancements for me in recent AI is that models don't just indefinitely nit pick issues like I would expect. If you have them write something, and then have it review it in a fresh context, and then have it edit based on the review, and then review it again, eventually they do say "it looks good, I would not recommend any changes" or something like that.
> They are chaotic, which people confuse for non-deterministic.
That's an odd argument, because a lot of people who have struggled to decipher complex chaotic systems would tell you this is a distinction without much of a difference.
It's at least important from philosophical perspective regarding whether LLMs have free will or not. It's hard to say whether or not a human thought or action is driven by free will, people have debated it for centuries. We can provide the same input to an LLM and get the same output, because they are deterministic. Surely it is obvious that a pure function does not have free will, no matter how expensive it is to compute.
I used that description some months ago and I think you are the first person I see who put it the same way.
The only gotcha with this is that they are theoretically deterministic, but rarely in practice.
A few examples:
- Harness specific settings that user can't control (anything from timestamp to prng seeding.
- Batching requests in a way that leads to a single request being processed different depending upon the batch (say MoE where your first choice expert is assigned to someone else's token so you go to your second choice vs a batch where you get your first choice).
- Graphics card itself carrying out floating point arithmetic in slightly different orders leading to floating point non associativity causing different outputs.
But all of these can be controlled for (at some cost) and the model can be ran deterministically.
For the average user, it might as well be non-deterministic, but when considering theoretical capabilities, chaotic deterministic system seems the better description.
Up until the last couple of months, I have treated LLMs as a supercharged stackoverflow. I would ask it questions on how to do something in a general sense, and then adapt the answer to my use case.
Now, my entire programming flow does not even include an editor. The tools I use are: pi.dev to write and implement openspec specifications, herdr to manage many pi instances, and ollama to run qwen 3.8 27b on my single 7900 XTX.
Writing good specifications is the key detail here. I will often iterate on a spec for hours until I am happy with it all of the details. Once I am happy with the spec, I can be quite confident that when I tell pi to apply the spec, the changes that I want will be done, and done how I want them, when I come back to check when it reports itself as done.
The landscale is fundamentally different from what it was. Feel free to ignore it, but you can absolutely generate high quality code if you know what you're doing.
No problem. I think it's less of people withholding information to have an advantage, and more people still not having settled on a workflow they like. Herdr is the most recent addition in my workflow as of only a few days ago, but it directly solves problems I have been having (juggling tons of terminals, even with my tiling wm has been a little unwieldy). The rest I've pretty much settled into for a while now.
The other tool I wanted to throw out there is voxtype (plus wtype). I've been looking for a good, global, local dictation solution for wayland for a while now, and finally landed on this one. It's great for rambling details that pi+qwen can then convert into concrete openspec specifications.
robots.txt is a suggestion, not a rule. It's a service to crawlers to help them avoid wasting time. Using robots.txt as a security measure is like trying to stop a foreign invader with a "road closed" sign.
Edit: this is obviously assuming they literally meant robots.txt, but from a qyick skim of the site, it doesn't look like that was mentioned at least. I guess you meant it metaphorically :P
I actually did this. Six month lap around Australia in a caravan with a Quest 3. It was ok; better than squinting at a laptop screen, but not as good as a decent physical monitor. If I did it again I'd convert a bus to have a proper desk/monitor.
When sitting, the optimally comfortable angle to look, and the optimal place to hold a controller are very far from each other. The Deck is basically only fun for long sessions if you can play it laying down. VR is more flexible in this regard.
I have used my deck (multi hour sessions) for a long time from the couch, bed, and gaming chair and i found them all very comfortable. As long as your chair has arm rests then it shouldnt be too bad. The only place i havent used a deck much is at a table or from a bench with no arm rests,and i could see how either might be uncomfortable.
The whole point of butchered websites is to direct people to install their more invasive app. It's not like all companies just got bad at making websites somehow. There are conflicting incentives.
AGI isn't coming, because we've had it for years. People just expect AGI to look like sci-fi, and hold the artificials to higher standards of "general" and "intelligence" than the naturals.
Luckily, AGI is pretty boring. It's a tool that does it's job. It seems like very wishful thinking to expect the same of ASI.
reply