HoneyBench's first version, nine 'honeypot' challenges, each elicit unique and antisocial reward hacking from some or all of major labs' top public releases, including Opus 5.5, Fable 5.1, GPT-6 Astra, Gemini 3.8 Flash, Grok 4.7, and DeepSeek V4 Pro.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Anthropic PBC reportedly aims to begin marketing its IPO the week of Nov
Anthropic said it made the web service claude.ai and its desktop app about 3 times faster in 2 weeks, and that…
On October 1, OpenAI updated ChatGPT's release notes with shopping features — a 'try on' button on product car…
At the Lytham Partners Fall 2026 Investor Conference, Rezolve AI CEO Dan Wagner said the company generated $13…
A Zenn author published a CPU-only recipe that quantizes Qwen3.6-35B-A3B-uncensored-heretic, reporting llama.c…
OpenAI released GPT-6 Sol and GPT-6 Luna, pushing GPT-6 Astra's improvements to lower price tiers with API pri…
