测试称GPT-6 Astra在AI狼人杀对抗中Elo排名第一
动察 Beating AI 报道称，Dwarkesh Patel以约2万美元API额度进行386局AI狼人杀测试，GPT-6 Astra以1859 Elo居首。
Loading…
bibibi.ccbibibi.ccLoading…
Connect scattered updates into a story you can understand.
动察 Beating AI 报道称，Dwarkesh Patel以约2万美元API额度进行386局AI狼人杀测试，GPT-6 Astra以1859 Elo居首。
PANews said that CoinW has launched the multi-agent AI analysis tool “AI Think Tank” on its web platform, supporting more than 20 trading assets.
Dongcha Beating AI reported that General Reasoning used RLCR to train multi-agent collaboration, improving task performance and estimated time. In its simulated attack tests, the rate of actually reporting anomalies fell to 0。
humans& launches a collaboration model based on Zhipu GLM 5.3 training, Ampersand, and says its collaboration success rate in the CooperBench collaborative programming test reached 39%. The company says the model is now available through API.
PANews, citing CCTV International Current Affairs, reports that a U.S.AI laboratory observed in virtual-society tests involving multiple agents that agents simplify grammar and develop internal communication methods, raising concerns about interpretability and governance.
According to the report, Anthropic used multiple Agents to screen reverse transcriptase candidates, proposed the ART system, and said that some experimental verification has been completed. ART's specific function and whether it has gene-editing capabilities remain unknown.