Petri (auditing tool)
Petri is an open-source tool, released by Anthropic, that automates parts of AI alignment auditing by using one AI model to probe another and a third to score what happens.
Explore Anthropic through related topics and the articles other pages reference most.
Articles that also belong to these categories. Counts cover all of Anthropic.
Showing 121-136 of 136 articles
Petri is an open-source tool, released by Anthropic, that automates parts of AI alignment auditing by using one AI model to probe another and a third to score what happens.
Project Glasswing is a restricted-access cybersecurity program run by Anthropic that gives selected companies, open-source maintainers and government bodies early use of its most capable Claude models for…
Quantum circuit design with Claude is a research project, published by Anthropic on 16 October 2026, in which the large language model Claude Mythos 5 designed reversible quantum circuits for eight…
Sabotage evaluations are a set of tests, introduced by Anthropic in October 2024, that try to measure whether a frontier language model is capable of covertly subverting human oversight, decision-making, and…
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet is the May 21
Scion is an in-house version control system built by Anthropic to replace git for the company's internal monorepo.
"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training" is a January 2024 Anthropic research paper (arXiv:2401.05566, submitted 10 January 2024) that deliberately trained large language…
Task budgets are an Anthropic API feature, in beta, that lets a developer tell the model how many tokens it has for a full agentic loop, including thinking, tool calls, tool results, and output.
Thariq Shihipar is a software engineer and startup founder who worked on Claude Code, Anthropic's agentic coding tool, from 2025 until October 2026.
The Anthropic Institute is a research organization within Anthropic dedicated to studying the societal challenges posed by increasingly powerful artificial intelligence systems.
Tom B. Brown is an American artificial intelligence engineer and researcher best known as the lead author of "Language Models are Few-Shot Learners," the 2020 paper that introduced GPT-3.
Towards Monosemanticity is an October 2023 mechanistic interpretability paper from Anthropic that used a sparse autoencoder to decompose the internal activations of a small language model into thousands of…
Toy Models of Superposition is a September 2022 mechanistic interpretability paper from Anthropic that shows how a neural network can represent more features than it has dimensions by packing them into…
Universal Music v. Anthropic is the common name for a federal copyright lawsuit that Universal Music Publishing Group, Concord, and ABKCO Music filed against Anthropic on January 28, 2026
Voyage-3 is a family of general-purpose text embedding models developed by Voyage AI, launched in September 2024 with voyage-3 and voyage-3-lite, expanded in January 2025 with voyage-3-large, and refreshed in…
"We Must Pace the Frontier" is an essay by Dario Amodei, chief executive of Anthropic, published on his personal website on Saturday, September 12, 2026.