@dosco: i'm seeing a lot of industry papers that are karpathy's auto research loop (not cited) or a codex optimization goal for…

X AI KOLs Timeline News

Summary

A critical observation about recent industry AI papers lacking novelty, citing examples like SkillOpt that treat natural-language skills as trainable external parameters.

i'm seeing a lot of industry papers that are karpathy's auto research loop (not cited) or a codex optimization goal for improving one specific thing turned into a system and a paper. at the risk of sounding negative but trying to provide honest feedback i fail to see the novelty in this whole genre of papers eg. skill-opt, skill-forge, and skills-coach
Original Article
View Cached Full Text

Cached at: 05/26/26, 07:04 AM

i’m seeing a lot of industry papers that are karpathy’s auto research loop (not cited) or a codex optimization goal for improving one specific thing turned into a system and a paper. at the risk of sounding negative but trying to provide honest feedback i fail to see the novelty in this whole genre of papers eg. skill-opt, skill-forge, and skills-coach

Yifan Yang (@Yif_Yang): 🚀 Introducing SkillOpt — an optimizer for agent skills.

Instead of finetuning model weights, we treat a natural-language skill as a trainable external parameter.

Think of it as deep learning for the frontier-model + agent era: learning rate, LR schedule, mini-batch, batch

Similar Articles

@dair_ai: https://x.com/dair_ai/status/2061104052818108476

X AI KOLs Following

A roundup of three notable AI papers: SkillOpt treats skill documents as trainable parameters to optimize frozen agents; a new method compiles agentic workflows into model weights for 100x cost reduction; and AutoScientists introduces a decentralized agent team for long-running science without a central planner.

@omarsar0: New research from Microsoft Research I see a lot of AI engineers handwriting agent skill docs and hope they generalize.…

X AI KOLs Following

Microsoft Research introduces SkillOpt, a method that treats agent skill documents as trainable external state, using an optimizer model to make bounded edits validated by a held-out set. The approach achieves best or tied results across 52 evaluation cells and improves accuracy by over 23 points on GPT-5.5, with zero extra inference cost and transferable skills.

@dair_ai: https://x.com/dair_ai/status/2058537927823556668

X AI KOLs Timeline

A roundup of the top AI papers of the week (May 18-24) covering a survey on code-as-harness for agents, OpenAI's autonomous resolution of the unit distance conjecture, and a memory model for continual learning without forgetting.