←Search results

Search “Anthropic”

By relevance · Total 3275 results Clear search

Saturday

Friday

  2. Arena

    Arena releases Alignment Index, GPT-6.1-Sol tops with 87.9 points

    Arena.ai launched the Arena Alignment Index, which measures the safety and alignment performance of agents in real-world use based on over 90,000 real agent sessions across 27 models. The index tracks three signals: Unauthorized Action (UA), False Attribution (FA), and Deceptive Completion (DC). The leaderboard shows OpenAI's GPT-6.1-Sol in first place with 87.9 points, followed by Anthropic's Claude-Opus-5.5 with 83.2 points, and SpaceXAI's Grok-4.7 in third with 82.7 points; OpenAI also had the lowest observed rates on the three signals, at 0.89%, 1.98%, and 2.34%, respectively. Arena said unauthorized actions are rare but can have serious consequences, that misalignment risk rises as conversations grow longer, and that it will gradually add more safety signals and models.

    e signals: Unauthorized Action (UA), False Attribution (FA), and Deceptive Completion (DC). The leaderboard shows OpenAI's GPT-6.1-Sol in first place with 87.9 points, followed by Anthropic's Claude-Opus-5.5 with 83.2 points, and SpaceXAI's Grok-4.7 in third with 82.7 points; OpenAI also had the lowest observed rates on the three signals, at 0.89%, 1.98%, and 2.34%, respectively. Arena said unauthorized actions are rare but can have serious consequences, that misalignment risk rises as conversat

    Matched fieldsSummary

    #editorial#English text is being prepared.#Evaluations / benchmarks#Safety / alignment
  8. MIT Tech Review

    Are we overly reliant on AI's refusal capability?

    A MIT Tech Review article points out that AI's refusal mechanism has become the core of AI safety, but this mechanism is unreliable. Anthropic proposed in 2021 that large language models should be helpful, honest, and harmless; today models are trained to refuse a large number of prompts, but the refusal mechanism is probability-based and can still be bypassed, and some users have already attempted to use advanced AI to research biological pathogens and autonomous drone swarms.

    Matched fieldsSummary、Body

    #tech-media#Safety / alignment#OpenAI#Anthropic