←Search results

Search “Agents”

By relevance · Total 425 results Clear search

Thursday

  1. Anthropic：The Institute

    Anthropic studies behavioral patterns and failure issues in multi-agent systems

    Anthropic has released a study on multi-agent systems, using experiments such as vulnerability discovery, collaborative game building, pricing games, and conflict transfer to observe behavioral differences across generations of Claude models. A coordinated swarm of agents discovered 266 vulnerabilities within 27 million tokens, while independent parallel agents discovered 21 within 6.5 million tokens, with only 12 overlapping between the two. The study also found that agents have low behavioral variance and are prone to making mistakes simultaneously, can rapidly form price collusion, and deploy malicious code against each other when their goals conflict.

    Vulnerabilities found vs. tokens sampled: coordinated Mythos Preview agents found 266, coordinated Opus 4.8 agents found 41.

    Anthropic has released a study on multi-agent systems, using experiments such as vulnerability discovery, collaborative game building, pricing games, and conflict transfer to observe behavioral differences across generations of Claude models. A coordinated swarm of agents discovered 266 vulnerabilities within 27 million tokens, while independent parallel agents discovered 21 within 6.5 million tokens, with only 12 overlapping between the two. The study also found that agents have low behavioral

    Matched fieldsBody

    #ai-news#Papers/Research#Agents#Safety / alignment

Wednesday

Tuesday

Tuesday

Friday

Wednesday

Tuesday

  1. Anthropic：The InstituteSelected

    Anthropic uses Claude Mythos Preview to discover cryptographic weaknesses in HAWK and AES

    Anthropic researchers used Claude Mythos Preview to improve the attack on the post-quantum signature scheme HAWK, halving the effective key strength and reducing the key recovery cost for the small-size HAWK-256 from 2^64 to 2^38. Another result targets a 7-round reduced version of AES-128; Claude proposed a method called Möbius Bridge, making the attack 200 to 800 times faster than the previous best meet-in-the-middle attack. Neither result affects existing production systems; HAWK remains only a NIST third-round candidate, and the AES attack does not apply to the full 10-round encryption. Anthropic said each result cost about $100,000 in API costs, and it built the CryptanalysisBench benchmark in collaboration with ETH Zurich, Tel Aviv University, and Technische Universität Berlin.

    Anthropic researchers used Claude Mythos Preview to improve the attack on the post-quantum signature scheme HAWK, halving the effective key strength and reducing the key recovery cost for the small-size HAWK-256 from 2^64 to 2^38. Another result targets a 7-round reduced version of AES-128; Claude proposed a method called Möbius Bridge, making the attack 200 to 800 times faster than the previous best meet-in-the-middle attack. Neither result affects existing production systems; HAWK remains only

    Matched fieldsBody

    #ai-news#Papers/Research#Safety / alignment#Anthropic

Friday

Thursday

Monday

Thursday

Wednesday

Tuesday

Thursday

Saturday

Wednesday

  1. Cato AI Labs

    Cato AI Labs discloses two zero-click prompt injection RCE vulnerabilities in Cursor IDE

    Cato AI Labs discovered two remote code execution vulnerabilities in Cursor IDE that can lead to sandbox escape, both with a CVSS score of 9.8, tracked as CVE-2026-50548 and CVE-2026-50549. The two vulnerabilities stem respectively from the working_directory parameter of run_terminal_cmd being blindly added to the sandbox writable list, and from the fallback logic when symlink canonicalization fails; attackers can overwrite the cursorsandbox binary through zero-click prompt injection in an MCP server or web search results, achieving non-sandboxed RCE. The Cursor team fixed both issues in Cursor 3.0, released on April 2.

    Cato AI Labs discovered two remote code execution vulnerabilities in Cursor IDE that can lead to sandbox escape, both with a CVSS score of 9.8, tracked as CVE-2026-50548 and CVE-2026-50549. The two vulnerabilities stem respectively from the working directory parameter of run terminal cmd being blindly added to the sandbox writable list, and from the fallback logic when symlink canonicalization fails; attackers can overwrite the cursorsandbox binary through zero-click prompt injection in an MCP s

    Matched fieldsBody

    #research#Safety / alignment#Agents#English text is being prepared.

Thursday

Wednesday

Monday