5 appearances on the backlist front page in the last 30 days.
Biggest difference between Codex vs Claude Code: Codex won't stop working towards a /goal. CC quits on hard tasks and needs encouragement to keep going. So weird. BUT Codex is pretty bad at intermediate summaries. Its outputs read like eso
I think there's a cleaner version of this question: What's the best GSM8k solver that fits in <2MBs that doesn't include (leaks of) test data.
The best symbolic solver for GSM8k (i.e., a pure python program) achieved a ~15% test error on GSM8k, which is kind incredible considering Llama 13B achieved the same :) Both Codex and CC seemed frustrated when pushed to grind beyond 15% a
Very rarely you stumble on a method that's simple, obvious in hindsight, free, and touches on every problem you care about: CLI agents, continual learning, self-improvement, world models. ECHO is one of those
btw we measured this in Memento: flushing your KV cache leads to measurably worse performance, no matter how good the model is https:// x.com/DimitrisPapail /status/2041974013950373901?s=20 …