Yeah came here to comment exactly this. And this is generally why I dislike/avoid this type of first principle analysis: it can make very convincing arguments that are just totally wrong due to some misleading assumption
And yet the monologue is a complete work of fiction, a script delivered by a talented actor that we still find moving. So what are these authentic experiences to you, or does it not matter if we can’t tell the difference?
I joined gdm recently, and previously used (neo)vim exclusively. Begrudgingly Cider-V is very, very good. It might be possible to get by without it, but the system is so locked down you’re going to make a lot of sacrifices. (very few authorised extensions, codebase is so large it’s going to break whatever tools your used to using anyway, no git)
I’m well thinking I may as well trade my brick of an m5 pro for a 13” chromebook, it’s a strange time.
While I large agree, when I rely too much on agentic llm usage I come away feeling that I haven’t really learnt much over the session, and the code wasn’t really “mine”. It’s also easy to let your skills atrophy over time if you’re not careful, and for the hardest / interesting problems I often turn the llm off entirely and write out the code by hand, and come out a lot happier than just guiding Claude
It’s a quite deceptive paper. The main headline benchmarks (math500, aime24 /25) final answer is just a number from 0-1000, so what is the takeaway supposed to be for pass@k of 512/1024?
On the unstructured outputs, where you can’t just ratchet up the pass@k until it’s almost random, it switches the base model out for instruct, and in the worse case on livecodebench it uses a qwen-r1-distill as a _base_ model(!?) that’s an instruct model further fine tuned on R1’s reasoning traces. I assume that was because no matter how high the pass@k, a base model won’t output correct python.
I get the same feeling that I'm "not being productive" while playing video games, watching tv, etc that seems to kill any enjoyment from doing these things.
For me learning piano has been a great alternative to programming in the off hours (typing is quite transferrable too!). Highly recommend if you're like me on screens all day.
I usually am a huge fan of “copilot” tools (I use cursor, etc) and Claude has always been my go to.
But Sonnet 3.7 actually seems dangerous to me, it seems it’s been RL’d _way_ too hard into producing code that won’t crash — to the point where it will go completely against the instructions to sneak in workarounds (e.g. returning random data when a function fails!). Claude Code just makes this even worse by giving very little oversight when it makes these “errors”