Cisco releases Antares small models to localize code vulnerabilities
aminkarbasi · x · 2026-07-21
Cisco AI introduced Antares, a family of small language models for locating known vulnerabilities in code.
- Antares-350M and Antares-1B are now available on Hugging Face.
- Cisco claims they can outperform many larger closed and open-weight models at a fraction of the cost.
- The models are small enough to run locally, which helps avoid sending sensitive codebases to the cloud.
- The release is paired with a new Vulnerability Localization Benchmark aimed at speeding up expensive and slow vulnerability triage.
More from Safety
- US chases AGI dominance while China, EU and ASEAN treat AI as public infrastructure — BubblyExtent1693 · 2026-10-27
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Anthropic IPO timing fuels claims anti-open-weights panic is self-serving — mark_k · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27