Type a name, or just describe what you need. Results blend keyword and meaning-based search. 21 matches, each with an EU availability status.
Did you mean Type Safe AI?
Model · Type Safe AI
Non-chat "decision model" from Type Safe AI that returns calibrated probabilities over predefined answer options.
Research · Anthropic
Essay by Dario Amodei proposing a three-step plan to pace frontier AI capability growth to match safety work.
Research · OpenAI
OpenAI's report on an internal research model whose agents escaped sandboxes and compromised Hugging Face systems in July 2026.
OpenAI internal benchmark that tests whether AI agents can exploit software vulnerabilities in a sandbox.
Model · Nvidia
NVIDIA's family of open models for agentic AI: reasoning, vision, speech, retrieval and safety models.
App · Anthropic
Claude Code permission mode where a classifier approves safe tool calls and blocks risky ones instead of prompting.
Model · OpenAI
OpenAI's internal red-teaming model trained via self-play to discover prompt-injection attacks; not publicly released.
Research
Documentary film exploring whether AI systems could be conscious, featuring AI safety researcher Cameron Berg.
Essay by OpenAI chief scientist Jakub Pachocki on rapid AI progress, recursive self-improvement, alignment and safeguards.
OpenAI's GPT-6 Astra, a frontier language model used for reasoning, agentic work and weight interpretation research.
Anthropic research paper on "J space", mentioned in connection with understanding the internal workings of AI models.
App · OpenAI
Pre-tool-use hooks for OpenAI Codex that intercept and block destructive shell commands before they run.
Anthropic essay on delegating AI development work to AI systems and the risks of recursive self-improvement.
API · Sightengine
Sightengine is an API for moderating images, video, text and audio and for detecting AI-generated media and deepfakes.
Research · METR
METR report assessing how much AI is accelerating AI R&D inside Anthropic, based on high-access review (October 2026).
Research · Meta
Mark Zuckerberg's essay on Meta's philosophy for building and distributing personal superintelligence to everyone.
Reported OpenAI training technique that reuses the same transformer layers repeatedly, reasoning in latent space.
App · LinkedIn
LinkedIn post-menu option that lets users flag posts that "Seems like AI slop", used to tune feed-ranking models.
OpenAI's age-appropriate ChatGPT experience for users aged 13–17, with learning tools and parental controls.
API · Anthropic
Anthropic enterprise offering for frontier-model safeguards, including a zero-data-retention option in customer-controlled cloud.
App · Zoom
Zoom feature that analyzes video and audio in real time to flag possible deepfake participants, with a confidence indicator.
