ChexQuest is so much better than it has any right to be. Loved it as a kid

Lean would be so well suited to LLMs. I hope we see a resurgence in interest in languages like that

Formal proofs have so much potential in this context

Absolutely. A language being well suited to static analysis and "compiler driven development" matters a lot more with LLMs than with humans IMO

We're at the point of diminishing returns from scaling and RL is the only way to see meaningful improvements

Very hard to improve much via RL without some way to tell if the code works without requiring compilation

Logic based languages like Prolog take this to the logic extreme, would love to see people revisit that idea

I think arenas might be better memory management technique when vibe coding C, for this reason

Automattic and New Relic if we're looking within software

My experience with deepseek and Kimi is quite the opposite: smarter than benchmarks would imply

Whereas the benchmark gains seem by new OpenAI, Grok and Claude models don't feel accompanied by vibe improvement

Yeah and OpenAI's CPO was artificially commissioned as a Lt. Colonel in the US Army in conjunction with a $200M contract

Absurd to say Deepseek is CCP controlled while ignoring the govt connection here

Literally every time a Chinese model is discussed here we get this completely braindead take

There has never been a shred of evidence for security researchers, model analysis, benchmarks, etc that supports this.

It's a complete delusion in every sense.

Tons of routers, modems, embedded, are running Chinese software

The average person has been programmed to be distrustful of open source in general, thinking it is inferior quality or in service of some ulterior motive