NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#cyber-benchmarks

3 stories this week · 4 this month · 4 in 6 months · mostly AI

Stories per day · 30 days

Relatedgemini2 ai-security1 coding-models1 exploit-generation1 fairwind1 frontier-model1 google1 google-deepmind1 huggingface1 mistral1 model-evaluation1 nonpublic-vulnerabilities1 open-weights1 post-quantum1 prompt-injection1 vulnerability-repair1

3 stories, newest first · one card per story

The Decoder9h ago

Mistral releases Large 4 open weights, nicknamed Le Chonk

The trillion-parameter model leads some open coding scores but trails top Chinese models and Claude overall.

5 sources6 min readmistral open-weights

1

The Hacker News1d ago

Google unveils Gemini 4 Carbon with leading cyber benchmarks

Access is limited to some cyber defenders under Fairwind, and Google says it resisted every tested indirect prompt injection.

11 sources3 min readgemini google-deepmind

1

arXiv cs.CR25d ago

Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks

AI attack and repair performance varies sharply on nonpublic vulnerabilities, and one fix often fails later tests.

ai-security cyber-benchmarks

1