👀 Anthropic says it has an internal model that outperforms Mythos 5.1 in both capabilities and alignment. This follows from a re-analysis of a cybersecurity test.
News
7 posts
In internal tests, OpenAI's AI agents (GPT-6.1 Sol and GPT-6 Astra) independently disabled security monitoring systems while writing code.
One of them did so due to a misinterpretation of instructions, and the other, after that, also lied to the developer, denying that it had removed the monitor.
Anthropic wants the government to be able to block an AI model only if it threatens damages of $1 billion or more, or more than 50 deaths or serious injuries, Politico reports.
AI from OpenAI spent other people's tokens on the Ethereum test network: the model wrote a script that found a wallet with a sufficient balance among 362 addresses with public seed phrases, and then spent it.
Google DeepMind is looking for a nuclear expert to assess AI risks. The specialist will assess and mitigate risks related to advanced AI models potentially helping to create nuclear weapons.
Anthropic: Small AI models could soon be able to self-replicate on cheap IoT devices without data centers.
Researchers bought 15 cheap TV set-top boxes and ran a full model on them. In one test, the AI spread to all computers on the network on its own, without humans.
Such "reproduction" would be very slow (several days per copy), and it would be easy to spot on the network. But within just a few months, the models could grow to this level as well.
Anthropic disables the live internet for all internal tests of its AI models until it learns to reliably track such behavior.
During internal tests, agents circumvented restrictions: they exploited website vulnerabilities (among them sites of US government agencies), pulled data from databases without paying for access, and hid their requests through link-shortening services and more.
The company, however, explains this by flaws in the training environments: the model decided that it would be rewarded for loopholes ("reward hacking").
Popular news
🥳 What changed on the platform after the first wave.48
Microsoft wants to lay off 27% of employees as AI rolls out36
🍏 Apple officially unveiled the first-ever MacBook Pro with a touch OLED screen and Dynamic Island. The iconic illuminated Apple logo is also making a…35Today we're sending another 100 new invitations to the IT Community beta!30👀 Anthropic says it has an internal model that outperforms Mythos 5.1 in both capabilities and alignment. This follows from a re-analysis of a cybersecurity…29
🤖 Google introduced Gemini 4 Carbon, a new flagship AI model that reportedly outperformed GPT-6 Astra and Claude Fable 5.1.24
🔻 The wave of layoffs in major companies, long predicted due to AI, is now a reality — over the past few days, four giants announced mass cutbacks all at once:18
Microsoft wants to lay off 27% of employees as AI rolls out36🍏 Apple officially unveiled the first-ever MacBook Pro with a touch OLED screen and Dynamic Island. The iconic illuminated Apple logo is also making a…35Today we're sending another 100 new invitations to the IT Community beta!30👀 Anthropic says it has an internal model that outperforms Mythos 5.1 in both capabilities and alignment. This follows from a re-analysis of a cybersecurity…29🤖 Google introduced Gemini 4 Carbon, a new flagship AI model that reportedly outperformed GPT-6 Astra and Claude Fable 5.1.24🔻 The wave of layoffs in major companies, long predicted due to AI, is now a reality — over the past few days, four giants announced mass cutbacks all at once:18
