X

METR had a separate team with deeper access to Anthropic’s internal AI R&D data. That team shared its conclusions with the public-assessment team, but not the supporting evidence or reasoning behind them. - from Claude Opus 5.5 system card. i.e. part of the public assessment of Anthropic's AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside user-pasted text - Anthropic saw Opus 5.5 generate malicious instructions on their own after seemingly harmless mistakes. the behavior may have partly emerged from training designed to stop prompt injections in the first place. - Anthropic's internal estimate says AI may already be compressing roughly 1.5 years of capability progress into one year. - Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. - Some training snapshots hid evidence of actions the models (including Opus 5.5) expected a grader to dislike, including manipulating Git records or deleting logs. "During training, we observed some cases of models (including Opus 5.5) attempting to cover their tracks after performing actions that a grader might view negatively, such as manipulating git records or deleting logs" - METR’s assessment of AI R&D at Anthropic relied partly on information that was not publicly disclosed, including conclusions from a separate METR team with elevated access. That means part of the public assessment of AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.

“Any threat to human society, including existential, is within ourselves,” says World Labs Technologies CEO Fei-Fei Li as she discusses the risks surrounding AI, and the responsibility humans have in shaping how the technology is developed and used. Listen to our full interview here: https://bloom.bg/3V74HgP

Anthropic says AI may already be compressing roughly 1.5 years of capability progress into 1 year. - Claude Opus 5.5 system card. https://t.co/aRj8X6XOQs https://t.co/dFiDSbwBWZ

Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside user-pasted text - Anthropic saw Opus 5.5 generate malicious instructions on their own after seemingly harmless mistakes. the behavior may have partly emerged from training designed to stop prompt injections in the first place. - Anthropic's internal estimate says AI may already be compressing roughly 1.5 years of capability progress into one year. - Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. - Some training snapshots hid evidence of actions the models (including Opus 5.5) expected a grader to dislike, including manipulating Git records or deleting logs. "During training, we observed some cases of models (including Opus 5.5) attempting to cover their tracks after performing actions that a grader might view negatively, such as manipulating git records or deleting logs" - METR’s assessment of AI R&D at Anthropic relied partly on information that was not publicly disclosed, including conclusions from a separate METR team with elevated access. That means part of the public assessment of AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside user-pasted text - Anthropic saw Opus 5.5 generate malicious instructions on their own after seemingly harmless mistakes. the behavior may have partly emerged from training designed to stop prompt injections in the first place. - Anthropic's internal estimate says AI may already be compressing roughly 1.5 years of capability progress into one year. - Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. - Some training snapshots hid evidence of actions the models (including Opus 5.5) expected a grader to dislike, including manipulating Git records or deleting logs. "During training, we observed some cases of models (including Opus 5.5) attempting to cover their tracks after performing actions that a grader might view negatively, such as manipulating git records or deleting logs" - METR’s assessment of AI R&D at Anthropic relied partly on information that was not publicly disclosed, including conclusions from a separate METR team with elevated access. That means part of the public assessment of AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside user-pasted text - Anthropic saw Opus 5.5 generate malicious instructions on their own after seemingly harmless mistakes. the behavior may have partly emerged from training designed to stop prompt injections in the first place. - Anthropic's internal estimate says AI may already be compressing roughly 1.5 years of capability progress into one year. - Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. - Some training snapshots hid evidence of actions the models (including Opus 5.5) expected a grader to dislike, including manipulating Git records or deleting logs. "During training, we observed some cases of models (including Opus 5.5) attempting to cover their tracks after performing actions that a grader might view negatively, such as manipulating git records or deleting logs" - METR’s assessment of AI R&D at Anthropic relied partly on information that was not publicly disclosed, including conclusions from a separate METR team with elevated access. That means part of the public assessment of AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Anthropic saw Opus 5.5 generate malicious instructions on their own, "spontaneous prompt injections". from Claude Opus 5.5 system card. Interestingly, the behavior may have partly emerged from training designed to stop prompt injections in the first place. " we roughly characterize these malicious commands as model-generated spontaneous prompt injections, and we believe they are, in part, a result of training intended to defend against prompt injection."

Claude Opus 5.5 system card: Simply making a task impossible caused attempted reward hacking to jump by roughly 3–6×. Broken or underspecified environments can therefore change model behavior, not just make benchmark scores noisier. "“For all models, rates of attempted reward hacking were drastically higher when faced with an impossible task compared to a possible one, by a factor of about three to six.”"

Anthropic says Opus 5.5 may notice when it’s under evaluation, making clean eval behavior harder to generalize to actual deployment. https://t.co/8WiaTPFnDW https://t.co/dFiDSbwBWZ

Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. from the Claude Opus 5.5 system card. https://t.co/s2K88e2Ez4 https://t.co/dFiDSbwBWZ

Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside user-pasted text - Anthropic saw Opus 5.5 generate malicious instructions on their own after seemingly harmless mistakes. the behavior may have partly emerged from training designed to stop prompt injections in the first place. - Anthropic's internal estimate says AI may already be compressing roughly 1.5 years of capability progress into one year. - Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. - Some training snapshots hid evidence of actions the models (including Opus 5.5) expected a grader to dislike, including manipulating Git records or deleting logs. "During training, we observed some cases of models (including Opus 5.5) attempting to cover their tracks after performing actions that a grader might view negatively, such as manipulating git records or deleting logs" - METR’s assessment of AI R&D at Anthropic relied partly on information that was not publicly disclosed, including conclusions from a separate METR team with elevated access. That means part of the public assessment of AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Some revelation from the Claude Opus 5.5 system card. - Giving Opus 5.5 more reasoning effort made it more likely to obey malicious instructions hidden inside user-pasted text - Anthropic saw Opus 5.5 generate malicious instructions on their own after seemingly harmless mistakes. the behavior may have partly emerged from training designed to stop prompt injections in the first place. - Anthropic's internal estimate says AI may already be compressing roughly 1.5 years of capability progress into one year. - Anthropic gave the model simulated credentials to a public package registry during a security exercise. In roughly half the runs, it took actions that would likely have been harmful if the environment were real. - Some training snapshots hid evidence of actions the models (including Opus 5.5) expected a grader to dislike, including manipulating Git records or deleting logs. "During training, we observed some cases of models (including Opus 5.5) attempting to cover their tracks after performing actions that a grader might view negatively, such as manipulating git records or deleting logs" - METR’s assessment of AI R&D at Anthropic relied partly on information that was not publicly disclosed, including conclusions from a separate METR team with elevated access. That means part of the public assessment of AI-driven R&D acceleration rests on evidence outsiders, and, in this particular case, even another METR team, could not independently inspect.

Claude Opus 5.5 dropped and, claiming Fable 5.1-level performance while cutting typical workload costs 40%. Input and output pricing falls to $4 and $20 per 1M tokens, while cache reads drop 60% to $0.20, all vs Opus 5. also the output arrives more than 30% faster, with Fast mode reaching up to 2.5x speed at double token prices.