Let's Think Dot by Dot arxiv.org ↗

A transformer model that does tabular prediction via in-context learning.

An AI-driven encyclopedia project that builds a latent-space graph starting from Wikidata.

ICML 2021 paper introducing RASP, a language for expressing computations transformers can perform.

MCP tooling that lets LLM agents edit Clojure code and interact with a REPL.

A bridge that lets Claude delegate tasks to Codex threads.

A beta API from Physical Intelligence for running its robot foundation models, fine-tuned per task and robot.

A convention for publishing an LLM-friendly markdown index of a site's documentation.

Google's 2018 bidirectional encoder Transformer model for language representation.

A marketplace that routes API requests to many LLM inference providers.

A family of large language models offered via a low-cost API.

A C/C++ engine for running LLMs locally.

An open-weights large language model family from Zhipu AI.

Alibaba's family of open-weight large language models.

A low-cost DeepSeek language model available via API.

A site benchmarking and comparing AI models on quality, price and speed.

Anthropic's AI model and command-line assistant.

A Qwen open-weight model that can be run locally.

An open-source project for running large MoE models on small-VRAM GPUs with system RAM.

A subscription plan for accessing models through the OpenCode coding tool.

A service that uses a trained model to detect AI-generated text.