695 karma · joined July 12, 2015
I also had a lot of problem due to async primitives with sqlalchemy - there's some tricky stuff with asyncio.gather vs TaskGroup and how sqlalchemy session works with it to be able to compose code easily.
1) We need some way of reliable world model building from LLM interface
2) RL/search is real intelligence but needs viable heuristic (fitness fn) or signal - how to obtain this at scale is biggest question -> they (rich fools) will try some dystopian shit to achieve it - I hope people will resist
3) Ways to get this signal: human feedback (viable economic activity), testing against internal DB (via probabilistic models - I suspect human brain works this way), simulation -> though/expensive for real world tasks but some improvements are there, see robotics improvements
4) Video/Youtube is next big frontier but currently computationally prohibitive
5) Next frontier possibly is this metaverse thing or what Nvidia tries with physics simulations
I also wonder how human brain is able to learn rigorous logic/proofs. I remember how hard it was to adapt to this kind of thinking so I don't think it's default mode. We need a way to simulate this in computer to have any hope of progressing forward. And not via trick like LLM + math solver but some fundamental algorithmic advances.
Can anyone who read this suggest something to use to scan room geometry using camera only in real-time (with access to beefy NVIDIA computer if needed) for drone navigation purposes?
All these "agentic" things make these models so confused that it almost never gives good results in my testing.
Example: You remove some function, you also remove all uses of it. You can't use not existing variable etc. This could be trained on well commited git repos or stalking/stealing the work of developers via editor
His name could be loosely translated as „Glorious Achievement-Cherry”.
Agree that JSX is great (but styles like in Svelte also).
Anyway I think some novel training method is needed and I’m with Yann on this. They could luck into good idea but with this budget chances are < 1%
Although I think people are the same, too big problem and you are getting lost unless taking it in bites, so seems like OpenAI implementation is just bad because o3 hallucination benchmark shouldn’t lead to such poor performance