Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer - MIT Technology Review

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) · 61%openai/gpt-oss-120b →
• PossiblePossibly related (embedding) · 60%openai/gpt-oss-20b →
• PossiblePossibly related (embedding) · 58%arashbehmand/mom-llm →
• PossiblePossibly related (embedding) · 58%mrwadams/stride-gpt →
• PossiblePossibly related (embedding) · 54%open-compass/opencompass →
• PossiblePossibly related (embedding) · 53%prime-radiant-inc/gauntlet →
• PossiblePossibly related (embedding) · 51%ninedter/pcap-hunter →

Covers

Covers (incoming)

Related across the graph