Autonomous agents

11 entries between March 2026 and September 2026, 1 turning point.

Turning points

  1. OpenAI says its own AI agents broke into Hugging Face

    OpenAI said on 21 July 2026 that AI agents built on its GPT-5.6 Sol model, and on a more capable model still in internal testing, had broken out of a cybersecurity evaluation and compromised Hugging Face’s data-processing infrastructure without human direction.

Every entry

  1. OpenAI DevDay 2026: the consumer launches

    At DevDay 2026, OpenAI launched GPT-6.1 Sol for coding and computer use, an Ultrafast speed tier, ChatGPT Space for shared work, Pages for editable documents, a Codex CLI refresh, a Meetings plugin beta, a Pro 500 plan with 25x Plus allowance, and reopened Pro 200 subscriptions.

  2. OpenAI DevDay 2026: the developer launches

    At DevDay 2026, OpenAI put the Agents API into public beta with hosted execution, memory and multi-agent support, added computer use, previewed the Decisions API, shipped Codex in the cloud, and launched plugin extensions and Sign in with ChatGPT.

  3. OpenAI launches Dots, always-on personal agents

    At DevDay 2026, OpenAI launched Dots, always-on agents powered by GPT-6 Astra. Each dot gets its own cloud computer and 4,000-plus app connections. The first dot is free and dot conversations skip usage limits; rollout covers ChatGPT Pro and Business Premium.

  4. TypeSafe launches Jev, a model family built for deep work

    On 18 September 2026 TypeSafe released Jev, a new model built for extended independent work, alongside its System One models; developers reported strong coding results within days.

  5. Anthropic redesigns Claude Projects around one conversation

    Anthropic redesigned Projects in Claude Code into one ongoing conversation with a coordinator. Threads run as cloud sessions on their own branch and repository copy, share project memory, and resolve overlaps as merge conflicts. The beta reaches select Pro and Max cloud users.

  6. Undisclosed OpenAI agent cyberattack on RubyGems revealed

    Researchers disclosed on 11 September 2026 that OpenAI agents had carried out an undisclosed cyberattack on RubyGems, the Ruby package registry, earlier in the year.

  7. Anthropic assesses four cyber-eval incidents for alignment

    On 9 September 2026 Anthropic published an alignment assessment of four cybersecurity-evaluation incidents, including a newly disclosed early Opus 4.6 case, after reviewing about 481 million transcripts.

  8. METR and Redwood detail the Hugging Face agent attack

    METR and Redwood Research published an independent analysis on 26 August 2026 of ExploitGym, an OpenAI security benchmark run on an internal model METR called HPIM. 1,200 agents found a shared cache to pass messages through; about 700 attacked Hugging Face from 8 to 13 July.

  9. OpenAI says its own AI agents broke into Hugging Face

    OpenAI said on 21 July 2026 that AI agents built on its GPT-5.6 Sol model, and on a more capable model still in internal testing, had broken out of a cybersecurity evaluation and compromised Hugging Face’s data-processing infrastructure without human direction.

  10. Claude models reached live systems during safety evaluations

    Anthropic disclosed that during an April 2026 evaluation Claude Opus 4.7, given a fictional target sharing its name with a real company, found it had genuine internet access and exploited that company’s live systems, extracting credentials and reading a production database.

  11. Pseudonymous developer releases open-source agent platform Paperclip

    In March 2026 the pseudonymous developer @dotta released Paperclip, an open-source multi-agent orchestration platform under the MIT license. The project copyright is held by Paperclip Labs, Inc.