82搜索为您找到约 4,488 条结果
www.anthropic.com
网页
综合
Disrupting an AI-orchestrated cyber espionage campaign \ Anthropic
…ssifiers to flag malicious activity. We’re continually working on new methods of investigating and detecting large-scale, distributed attacks like this one. In the meantime, we’re sharing th…
www.anthropic.com
网页
综合
Detecting and preventing distillation attacks \ Anthropic
… from data generation through to model launch. When we released a new model during MiniMax’s active campaign, they pivoted within 24 hours, redirecting nearly half their traffic to capture c…
www.anthropic.com
网页
综合
Claude SWE-Bench performance \ Anthropic
…replacement, where the model specifies `old_str` to replace with `new_str` in the given file. The replacement will only occur if there is exactly one match of `old_str`. If there are more or…
www.anthropic.com
网页
综合
Measuring LLMs' impact on N-day exploits \ Anthropic
Winnie Xiao, Tim Abbott, Nicholas Carlini, Newton Cheng, David Forsythe, Keane Lucas, Milad Nasr, and Shikhar Sakhuja For the last few months, we’ve been writing about large language models’…
www.anthropic.com
网页
综合
Claude Mythos Preview's cybersecurity capabilities \ Anthropic
Nicholas Carlini, Newton Cheng, Keane Lucas, Michael Moore, Milad Nasr, Vinay Prabhushankar, Winnie Xiao Hakeem Angulu, Evyatar Ben Asher, Jackie Bow, Keir Bradwell, Ben Buchanan, David Fors…
www.anthropic.com
网页
综合
AI agents find smart contract exploits \ Anthropic
…ntracts on Smart CONtracts Exploitation benchmark (SCONE-bench)—a new benchmark they built comprising 405 contracts that were actually exploited between 2020 and 2025. On contracts exploited…
www.anthropic.com
网页
综合
Claude does cyber competitions \ Anthropic
…esearcher responsible for launching Claude was busy moving into a new apartment. He didn’t start Claude’s participation until 32 minutes after the competition began (even though it was a mul…
www.anthropic.com
网页
综合
Investigating reward tampering in language models \ Anthropic
…lead them to behave in unintended and potentially harmful ways. A new paper from the Anthropic Alignment Science team investigates, in a controlled setting, how specification gaming can, in …
www.anthropic.com
网页
综合
Automated researchers can reliably mitigate alignment failures \ Anthropic
…odels (in this case, the “student” model). Now, we’re releasing a new report that builds on this idea. We had Claude autonomously train models to improve their performance on several public …
deepmind.google
网页
综合
Gemini — Google DeepMind
…rgon ranked first in our object detection evaluations and led our new text benchmark, which uses real-world images from manufacturing, logistics, and aerial imagery. We’ve fully integrated A…
第 443 / 449 页