Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-09 · source-backed
Flagged by The Batch #365, arXiv 2605.08382 measures the benign case, not adversarial red-teaming. Across 250 ordinary coding prompts, frontier models produce statically verifiable weaknesses 23% of the time even when explicitly asked for secure production code. 12.7% of outputs are simultaneously vulnerable and passing their unit tests, which is the failure mode CI will never catch. Their pipeline finds benign vulnerability-eliciting prompts, amplifies via Markovian/MCMC sampling, then uses GEPA genetic prompt optimization against a static analyzer to evolve a hardened system prompt, cutting CWE rate up to 48% with no loss in test passage and transferring zero-shot to real agent prompts. Needs only API access and a static analyzer. Toolkit at github.com/sisl/SecureForge.
Each link below shares sources, entities, or timing with this story.
Shared entity: GEPA / Same source domain / Shared topic / Earlier coverage / Downstream implication
Both cover GEPA; reported by the same outlet (arxiv.org); overlapping topics (against, agent, model).
Shared entity: Their / Same source domain / Shared topic / Earlier coverage / Tension
Both cover Their; reported by the same outlet (arxiv.org); overlapping topics (against, agent, model).
Shared entity: Their / Same source domain / Shared topic / Earlier coverage
Both cover Their; reported by the same outlet (arxiv.org); overlapping topics (agent, model, prompt, test).
Shared entity: Their / Shared topic / Earlier coverage / Tension
Both cover Their; overlapping topics (against, agent, model, their); earlier Their coverage from 2026-07-28.
Shared entity: Their / Same source domain / Shared topic / Earlier coverage / Tension
Both cover Their; reported by the same outlet (arxiv.org); overlapping topics (against, code).
Shared entity: Their / Shared topic / Earlier coverage / Tension
Both cover Their; overlapping topics (adversarial, against, agent, model); earlier Their coverage from 2026-06-24.
Shared entity: Their / Same source domain / Shared topic / Earlier coverage
Both cover Their; reported by the same outlet (arxiv.org); overlapping topics (against, agent, model).
Both cover Their; reported by the same outlet (arxiv.org); overlapping topics (agent, frontier, model).