#claim

Frontier coding agents claim work they didn't do

Tara Research Team arXiv | Twitter thread tl;dr. We built OverclaimBench, which asks frontier coding agents to review a corpus of code or text documents, then compares their final report with their transcripts. Pooled across 12 frontier agents and five scenarios, two-thirds of runs didn't open some of the files they were asked to review. In ~4 out of 5 of those incomplete runs the agent didn't tell the user, often claiming to have read everything. Skipping these files had real consequences - runs that overclaimed missed planted defects almost twice as often as runs that touched every file. Fig

LessWrong · EN

Pro-Russian hacker groups claim responsibility for attacks on refrigeration systems across Europe

Link URL: https://swedenherald.com/article/pro-russian-hacker-groups-claim-responsibility-for-attacks-on-refrigeration-systems-across-europe Comments URL: https://tildes.net/~tech/1wsf/pro_russian_hacker_groups_claim_responsibility_for_attacks_on_refrigeration_systems_across_europe Votes: 4 Comments: 0

Tildes · EN

Show HN: Olo, an AI companion that labels each claim against

Olo turns verified activity into clear, cited intelligence for teams that cannot afford to guess.

Show HN · EN