Prolific as ever! Small nitpick - the SBF interview link appears to be pointing at something else?
FYI I do find that aider using a mixed routing between r1 and o3-mini-high as the architect model with sonnet as the editor model to be slightly better than cursor/windsurf etc.
Or for minimal setup, this is what is ranking the highest on aider-polyglot test:aider --architect --model openrouter/deepseek/deepseek-r1 --editor-model sonnet
Is the bet for general purpose model still open? I guess it depends on the specific resolver/resolution criteria - considering that OpenAI have gotten the answer and solution to most of the hard questions. Does o3's 25% even count?
The "biologically imposed minimal wage" is definitely going into my arsenal of verbal tools. This is one of the clearest illustration of the same position that has been argued since the dawn of LW.
I think this is a rather legitimate question to ask - I often dream about retiring to an island for the last few months of my life, hangout with friends and reading my books. And then look to the setting sun until my carbon and silicon are repurposed atom by atom.
However, that is just a dream. I suspect the moral of the story is often at the end:
"Don’t panic. Don’t despair. And don’t give up."
I am a fool - what does RSI mean in this case? I couldn't find it in the og post.
I think that is just true. Now in hindsight, my mistake is that I haven't really updated sufficiently towards how the major players are shifting towards their own chip design capacity. (Apple comes to mind but I am definitely caught a bit off guard on how even Meta and Amazon had moved forward.) I had the impression that Amazon had a bad time in their previous generation of chips - and that new generation of their chips is focused on inference anyways.
But now with the blending of inference and training regime, maybe the "intermediaries" like Nvidia now gets to capture less and less of upside. And it seems more and more likely to me that we are having a moment of "going back to the basics" of looking at the base ingredients - the compute and the electricity.
I think this category of actors are neglected as a whole. (As well as SKH, micron etc.)
TSMC makes the chips for NVIDIA and everyone - I didn’t talk too much about them because they are already a lynchpin in many countries’ AI/national security policy (China PRC, Taiwan and at least United States). And by their nature, they are already under heavy surveillance for prosaic (trad. National security and chip self-sufficiency) reasons.
Note for posterity: “Let’s think step by step” is joke.
I downvoted this and I feel the urge to explain myself - the LLMism in the writing is uncanny.
The combination of “Let's think step by step”, “First…” and “Not so fast…” gives me a subtle but dreadful impression that a highly valued member of the community is being finetuned by model output in real time. This emulation of the “Wait, but!” pattern is a bit too much for my comfort.
My comment hasn’t too much to do with the content but more about how unsettled I feel. I don’t think LLM outputs are all necessarily infohazardous - but I am beginning to see the potentially failure modes that people have been gesturing at for a while.