newsMIT Technology Review AITrust 88 · LabPublished yesterdayLive · 1m ago
Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their defenses against cyberattacks. Last week the company released the latest version of its flagship LLM, GPT-5.6. OpenAI says that training it against GPT-Red made the model its most robust release yet. GPT-Red automates…
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%openai/gpt-oss-120b →
- PossiblePossibly related (embedding) · 53%open-compass/opencompass →
- PossiblePossibly related (embedding) · 53%arashbehmand/mom-llm →
- PossiblePossibly related (embedding) · 53%openai/gpt-oss-20b →
- PossiblePossibly related (embedding) · 52%mrwadams/stride-gpt →