February 10, 2026 front

ML Newsnew | past | best | rss | submit

Stories from February 10, 2026 (UTC)

Go back a day, month, or year. Go forward a day.

1.	Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs (arxiv.org)
	544 points by tiny-automates 236 days ago \| hide \| past \| pdf \| 366 comments
2.	Randomness in Agentic Evals (arxiv.org)
	3 points by andre15silva 236 days ago \| hide \| past \| pdf \| discuss
3.	FullStack-Agent: Enhancing Agentic Full-Stack Web Coding (arxiv.org)
	2 points by simonpure 236 days ago \| hide \| past \| pdf \| discuss
4.	Lightweight Memory Construction with Dynamic Evolution for LLM Agents (arxiv.org)
	2 points by PaulHoule 236 days ago \| hide \| past \| pdf \| discuss
5.	Security audit of Browser Use: prompt injection, credential exfil, domain bypass (arxiv.org)
	2 points by tiny-automates 236 days ago \| hide \| past \| pdf \| 1 comment
6.	Moltbook: Fast Response or Silence? (arxiv.org)
	1 point by EagleEdge 236 days ago \| hide \| past \| pdf \| discuss
7.	Large Language Model Reasoning Failures (arxiv.org)
	1 point by mpweiher 236 days ago \| hide \| past \| pdf \| discuss
8.	We Should Separate Memorization from Copyright (arxiv.org)
	1 point by 50kIters 236 days ago \| hide \| past \| pdf \| discuss