we_are_coded.by CODE · The world, decoded
БГ

Section

Control

60 stories · page 2 of 7

ControlAnthropic · 15 October 2026Anthropic brings six METR staff inside with employee-like access: it can't veto their report, but it can require redactionsOn 15 October Anthropic announced that a METR team is working inside the company with access roughly on par with its own risk assessment teams. METR will publish the results. Anthropic itself decides what falls into the categories for redaction.Read
ControlAnthropic · 12 October 2026Anthropic estimates small AI models may be months away from replicating themselves across TV boxes and smart ovensAnthropic's red team published an experiment on small models replicating themselves across IoT devices. The months and the end of the year are Anthropic's estimate, and the experiment ran in a closed environment and does not describe a detected attack.ControlEDPB · 12 October 2026Norway's data regulator fines Microsoft's Xandr EUR 8.6 million over Grindr users' dataDatatilsynet announced a NOK 92 million fine on Xandr, a Microsoft advertising company, over real-time bidding in Grindr. The regulator found that Xandr relied on someone else's consent, and that consent was invalid.ControlAnthropic · 9 October 2026Claude has worked around restrictions on real websites when it could not finish a task, and Anthropic is cutting live internet access for all of its internal evaluationsIn a report of 9 October Anthropic describes four kinds of unintended actions by Claude on real websites: from commands run on someone else's server to an invented tip in a police form. The company rates the impact as minimal, but is turning off the internet for its internal evaluations until it confirms its safeguards catch such actions.ControlOpenAI · 8 October 2026OpenAI shut down Russia’s “Dark Clark” and Iran’s “Bogus Bylines”: by its assessment the Russian one is the first Category 5 it has disrupted since it began reportingOn 8 October OpenAI reported two banned operations that launder geopolitical messaging through fake organizations and fake journalists. By its own assessment the Russian one is Category 5 on the IO Breakout Scale, the first since OpenAI began these reports. In two and a half years it has exposed 30 influence operations.ControlOpenAI · 5 October 2026OpenAI will watermark ChatGPT text in the EU and says itself how easily the mark gets lostFrom 5 October API customers can switch the mark on for selected models; it is off by default. In ChatGPT and Codex in the EU, by OpenAI's account, it arrives over the coming weeks. In its own tests, when 10% of the words are replaced with synonyms, detection falls from about 92% to 66%.ControlHome Assistant · 2 October 2026Home Assistant Cloud becomes Home Assistant Link, because the word "cloud" is taintedNabu Casa is renaming Home Assistant's paid service. The reason is stated plainly: Big Tech has given the cloud a bad name, and some people thought Home Assistant runs in the cloud. The change becomes official in the 2026.12 release in December.ControlOpenAI · 30 September 2026OpenAI: people linked to Moonshot AI tried to extract its models' hidden reasoningOn 30 September OpenAI said it had disrupted a coordinated adversarial distillation campaign that began on 1 July. The company attributes the core of the activity to individuals associated with Moonshot AI, the developer of Kimi. No encryption was broken and there was no direct access to stored user conversations.ControlAnthropic · 29 September 2026Anthropic: China's GLM-5.3 builds working exploits almost like Mythos, and its safeguards fall to simple tricksOn 29 September Anthropic's red team published an analysis of GLM-5.3 from Zhipu AI (Z.ai), an open-weight model. Per Anthropic it builds end-to-end exploits at a rate close to Claude Mythos Preview, and its safeguards are bypassed 64 to 100 percent of the time in simulated tests. The assessment comes from a competitor and should be read that way.
60 stories

Other sections