Bandit

Search everything

Mentions · 7d0
Mentions · 30d0
All mentions2
First seenSep 16, 2026
Last mentionedSep 19, 2026

Timeline

2 articles · newest first

Specification Before Generation: A Pre-Registered, Five-Model Paired Evaluation of a Specification Frame for LLM-Generated Code in Money, Time, Idempotency, and Access Tasks

A 267-word specification frame cut security defects in code from five frontier models, and never made any model worse.

Hugging Face daily papersSep 19, 20:00 UTC · Sep 19, 2026AI safety & security1 · 1 read

A Security Risk Assessment Framework for AI-Powered Development Tools

Researchers propose SRF, a framework showing AI-generated code from multiple development tools introduces vulnerabilities, worst in input and file handling tasks.

arXiv cs.CRSep 16, 13:36 UTC · Sep 16, 2026AI safety & security2

Appears with

SRFproduct · 1
Semgrepproduct · 1

Entities are extracted by the model from each article. First seen Sep 16, 2026, last mentioned Sep 19, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.