topic · 2 notes
LLM Evaluation, as it ships.
Engineering notes on LLM Evaluation by Samir Sengupta - each one read from primary sources on the day it happened, with what it changes for people building on it.
Fable 5.1 solved the Cyphral Distich cipher in 44 minutes and 176k tokens
Claude Fable 5.1 keyed Urquhart's 64-number Cyphral Distich to his 32 Proquiritations in 44 minutes and 176k tokens, then verified 285 octastich positions.
Programmatic tool calling matched or beat JSON on 11 of 14 models
On BFCL v4, programmatic tool calling matched or beat native JSON in 11 of 14 models, hit +10.6% on GPT-5.6, and stayed flat where JSON dropped 2.3%.
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.