Introducing EvoSkill v2: a system that automatically improves AI agent skills without changing the underlying model or runtime. It tests the agent, learns from its attempts, and rewrites its instructions to improve performance.
Our new paper compares EvoSkill v2 with SkillOpt by @MSFTResearch and SkillBoost by @AlibabaGroup on held-out tasks, reporting:
+23.6pts on τ3-bench banking with no skill, using Claude Haiku 5.5
+7.7pts over SkillOpt on SpreadsheetBench v2
+5.4pts over SkillOpt on τ3-bench banking
Who Owns an AI? A New Benchmark Wants to Find Out
As AI models are copied, distilled, and redistributed at scale, proving where they came from has become one of the industry's thorniest problems. Sen
https://t.co/w1iVtvgdCu
#AIOwnership#ModelFingerprinting#SentientFoundation
• Lexicographers planted fake words in dictionaries.
• Cartographers drew fake streets into maps.
• Artists hid their signatures inside the paint.
• AI builders embed fingerprints into their models.
History doesn't repeat itself, but it does rhyme.
Models cost millions to train and minutes to copy. Fine-tuning and distillation can erase where they came from.
Introducing the Fingerprinting Leaderboard, an open benchmark for model provenance — built so the proof lives in the weights, not the paperwork.
https://t.co/aHONvNd7o4
AI is the first medium that can be copied without leaving proof of origin.
When one model distills another, no one can prove it happened.
On October 14, that will change.
Catch up on the story so far: https://t.co/sALP9m9aP0