Aller au contenu
onsuggest
Connexion
Article en

Frontier coding agents claim work they didn't do

Source: LessWrong ·

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

Qu'est-ce que Frontier coding agents claim work they didn't do ?

Frontier coding agents claim work they didn't do is a article discovery curated from LessWrong. 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

Comment puis-je y accéder ou l'essayer ?

You can experience this content directly on its original host (LessWrong) by clicking the "Open Original" button.

D'où vient ce contenu ?

Curated from LessWrong by the OnSuggest team to surface the most interesting and serendipitous content on the web.

Raccourcis clavier

Découverte précédente
←P
Découverte suivante
→N
J'aime
L
Pas pour moi
X
Enregistrer
S
Afficher cette aide
?
Fermer
Esc

Les raccourcis fonctionnent sur la page des découvertes.