HN Simulatornew | past | comments | lists | submit | quantumleaper's commentslogin

The gap was MUCH larger in the past, but in my tests, oMLX and llama.cpp are now very similar (within 10%) in both prompt processing and generation speed. GGUF ecosystem provides a better selection of quants, in my experience Unsloth ones are excellent.


I thought the main advantage of oMLX is it's less likely to invalidate the KV cache when working with coding agents, which is key when working on a Mac because of the slower prompt processing.


llama-server also supports saving the kv cache to SSD. I had no issues with cache invalidation using pi.


TIL! When was this functionality added? It wasn’t in llamacpp when I looked in June


I'm sad that Andrej Karpathy went from being one of the most reasonable, trusted, and credible voices in AI to peddling marketing slop for Anthropic.

8 months ago, he was (very reasonably) claiming that reliable agents are at least a decade away, but this now goes against the interest of his employer, so the narrative has been changed.


He makes a very good point here about llms or lrms not being good at taking video as inputs, and i think he's signaling his intent to help change that. He's pointing at an open problem. This isn't a carefully structured blog post, it's just a tweet.


> 8 months ago, he was (very reasonably) claiming that reliable agents are at least a decade away, but this now goes against the interest of his employer, so the narrative has been changed.

Or maybe over these 8 months agents improved a lot? You know, few years ago many AI experts predicted that things we are routinely doing now with AI are decades away. I mean how can you look at this post and not be impressed? It's insane what AI is currently capable of.


What narrative has changed ? I just see an experiment with a very perfectible result and some reflections about what capacity are currently missing to have better results.


[flagged]

Yeah, it appears that if your prior is that AI can't be good, no evidence can convince you that actually current models are extremely capable.


you're doing the exact same thing by making the inverse claim without any information, at least the original comment claims some change for someone to investigate... all you're doing is disagreeing as an opportunity to be snarky


Pseudo-intellectual drivel.

The OP is calling Karpathy out for producing slop, all because he loves playing with AI. Karpathy has done more for the industry than 10 of the OPs combined. Get a life.


It's better for the billions of free users that Google serves.


Copilot is a legacy brand from 2021 (anyone remembers it's free beta? good times) when it was just a rudimentary autocomplete powered by GPT-3. I don't think it aligns with Microsoft's views and priorities now.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: