Skip to content

#开源/仓库

Today 0 items
Oct 15Thu
  1. Latent Space40

    Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash Bio

    On a podcast, Leash Bio's Ian Quigley explained how its DNA-encoded library (DEL) technology tames high-throughput protein-small-molecule interaction data and trained the Hermes model, which matches Boltz on public benchmarks using only the company's own data. The team also uncovered tens of thousands of lab-in-the-loop simulation data points, grew into Minos within two months, and today released a preprint, blog post, and open dataset for reinforcement learning where AI agents do verifiable scientific reasoning.

Oct 14Wed
  1. Simon Willison21

    web-edit 0.1a1

    Simon Willison released web-edit 0.1a1 on October 13. The original post is extremely brief, only mentioning his monthly LLM news email newsletter (curating the most important large language model developments each month, sponsored at $10/month), and offers no specific details about web-edit's functionality.

Oct 13Tue
Oct 9Fri
  2. Simon Willison37

    ttok 0.4

    Simon Willison released ttok 0.4, a CLI tool for counting tokens built on OpenAI's open-source tiktoken library. The update fixes Click warnings, updates CI, and adds a --list-models command to list available models. The tool can run via uvx, for example cat file.txt | uvx ttok to count tokens in any file.

Oct 8Thu
Oct 7Wed
  1. OpenAI News66

    Sharing AI progress in mathematics

    OpenAI released new results on its internal frontier model solving open mathematical problems, and published Lean proof formalizations and research details on GitHub.

    Why it matters: The article reports that OpenAI shared results from its internal frontier model on open math problems and released Lean formalized proofs and research details on GitHub.

  3. Hugging Face Blog43

    Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance

    The co-publishers with Hugging Face released Falcon-Emirati-7B, fine-tuned from the Falcon-H1-Arabic 7B variant to understand and generate Emirati Arabic dialect. The model uses a hybrid Mamba and Transformer attention architecture, trained on Emirati dialect web data, Emirati-culture MSA data, and synthetic data constrained by lexicon and style rules, with a context window supporting up to 128K/256K tokens.

  4. TechCrunch · AI45

    How AI decision models could change content moderation

    Musubi on Tuesday released PolicyLM-1.7B, a lightweight decision model for real-time content moderation, as an open-weights release. The model can apply content policies written in English to messages in under 50 milliseconds, with cost and speed close to the AI classifiers used by most social platforms, and requires no retraining when policies change. Decision models became a hot direction after TypeSafe AI released Jev in September, with OpenAI and Amazon following with competitors.

Oct 2Fri
Sep 30Wed
  1. Simon Willison55

    Photo Scrubber — local face blur & metadata removal

    Simon Willison shared Photo Scrubber, an experimental tool he built with GPT-6 Astra that automatically detects faces in photos and blurs them, avoiding sharing photos that identify strangers' faces. The tool uses Google's MediaPipe C++ library, compiled to WebAssembly via @mediapipe/tasks-vision, and employs the BlazeFace face detection model.

Sep 24Thu
Sep 22Tue
  1. Simon Willison35

    llm-typesafe 0.1a0

    Simon Willison released llm-typesafe 0.1a0, an LLM plugin supporting TypeSafe AI's newly launched Jev model. It can be installed with `llm install llm-typesafe` and used by setting a typesafe API key.

Sep 21Mon
  2. Hugging Face Blog64

    tokenizers v1: encode, decode and scaling, measured

    Hugging Face has released a candidate version of tokenizers v1; on an Apple M4 Max, single-threaded encoding is 3 to 30 times faster than v0.23, eight-thread scaling reaches 76% of linear, and the output token IDs are fully identical.

    Why it matters: The official write-up details the performance optimizations in tokenizers v1 along with reproducible benchmarks, letting readers assess the real benefits of upgrading for training and inference data feeding.

Sep 3Thu
  1. Hugging Face Blog73

    Give Your Coding Agents a Memory You Own

    Hugging Face has released funes, an open-source tool that turns existing agent session logs on your machine into searchable memory, supporting Claude Code, Codex, pi, and Hermes. It runs embedding and reranking locally with no account required, and can also bind to a private Hugging Face dataset for cross-machine sync. On the handoff-vs-recall benchmark, recall is 8x and 4x cheaper than writing handoff documents.

    Why it matters: It is an official open-source memory layer from Hugging Face with installation instructions and benchmark comparisons, so readers can evaluate whether it can reuse their existing coding agents' session logs.

Sep 2Wed
Jul 2Thu
  1. Mistral AI65

    Leanstral 1.5: Proof Abundance for All

    Mistral released the Apache-2.0 open-source model Leanstral 1.5, with 119B total parameters and 6B activated parameters, trained via mid-training, supervised fine-tuning and CISPO reinforcement learning.

    Why it matters: The official post discloses the full training pipeline, benchmark figures and real code verification cases, letting readers gauge how practical formal verification models are for mathematical proofs and open-source bug finding.

Jun 4Thu
May 2Sat