Skip to content

#编码

Today 2 items
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.

Aug 25Tue
  1. Hugging Face Blog61

    Granite 4.2 LLMs: How They're Built

    IBM released the Granite 4.2 reasoning model family, comprising 3B, 8B and 30B dense decoder models built on the Granite 4.1 base (pretrained from scratch on about 15T tokens, with a five-stage strategy extending context to 512K), post-trained with SFT and multi-stage GRPO reinforcement learning, all open-sourced under the Apache 2.0 license.

    Why it matters: The official disclosure covers the full training pipeline from pretraining and SFT to multi-stage GRPO and agentic RL, transferable to similar model-building workflows.

Aug 24Mon
  1. Import AI47

    Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye

    Import AI issue 470: METR research finds AI brings significant speedups to cybersecurity discoveries, modest contributions to math, but no measurable acceleration yet for optimizing AI research algorithms. Teams from multiple universities propose the SPADE framework, which co-evolves environment synthesis with agent capabilities via self-play, reaching an average score of 58.3 on a suite of game environments with Qwen3-30B-A3B, 5.3 above the baseline. This issue also introduces Hawkeye, for building better GPU kernels.

Aug 14Fri
  1. Google DeepMind72

    Introducing Gemini 3.7 Flash

    Google DeepMind released Gemini 3.7 Flash, positioned as its flagship model for coding and agents, just three weeks after Gemini 3.6 Flash.

    Why it matters: The official announcement includes multiple benchmark scores and the half-price pricing details, so readers can decide whether to switch to 3.7 Flash.

Aug 10Mon
  1. Hugging Face Blog78

    Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

    Meta today released Muse Glimmer, a 30B-parameter open-source multimodal model distilled from Muse under the Apache 2.0 license, aimed at privacy-focused local deployment and agentic uses like coding, document analysis, and personal assistance.

    Why it matters: The article provides architecture details, agent benchmark comparisons, and day-0 usage across inference stacks, helping readers evaluate local multimodal deployment options.

Aug 4Tue
  1. Microsoft Research73

    Orchard: An open framework for scalable agentic AI

    Microsoft Research has released Orchard, an open-source agent framework built around Orchard Env, a reusable Kubernetes-based environment service supporting training and evaluation of software engineering, web navigation, and personal assistant agents, with end-to-end training directly inside real harnesses such as Codex, OpenClaw, and ZeroClaw. Orchard-SWE reaches 69.7% on SWE-bench Verified with about 3B active parameters.

    Why it matters: Microsoft has open-sourced a reusable agent environment layer along with training recipes for three small models, letting readers gauge what small models can achieve on real tasks.

Jul 27Mon
Jul 26Sun
  1. Berkeley AI Research46

    Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

    Berkeley AI Research proposes the ABBEL framework, which replaces full interaction history with a natural-language belief state as the agent's working context and introduces belief grading to supervise summary content. On the CollabBench collaborative coding benchmark, ABBEL-rec-BG closes roughly 50% of the performance gap with full-context models, cuts training steps from 100 to 50, and uses significantly shorter peak context token lengths than the full-context setting.

Jul 21Tue
  1. Google DeepMind76

    Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

    Google DeepMind released three Gemini models: Gemini 3.6 Flash cuts output token usage by 17% versus 3.5 Flash on the Artificial Analysis Index, priced at $1.50/1M input and $7.50/1M output, with DeepSWE 49% vs 37% and OSWorld-Verified 83.0% vs 78.4%.

    Why it matters: The official article gives concrete pricing, token efficiency, and multiple benchmark numbers for the three new models, and explains the deployment scenarios each targets.

Jul 17Fri
Jul 1Wed
Jun 18Thu
May 29Fri
May 28Thu
  1. Mistral AI47

    AI Now Summit 2026

    At AI Now Summit 2026, Mistral unveiled a full-stack AI offering for industrial engineering, partnering with Airbus, BMW and ASML across design, simulation and production while ensuring data sovereignty. Its agent product Vibe was upgraded into a unified agent that handles long-horizon multi-step work, from deep research and coding to merging PRs. A 10 MW inference data center in Les Ulis, France, is slated to come online in Q3 2026.

  2. Mistral AI69

    Vibe gets to work.

    Mistral launched the unified AI agent Vibe, with Le Chat fully upgraded to Vibe; existing plans, history and settings migrate automatically. Work Mode targets long-horizon multi-step tasks spanning enterprise knowledge search, data analysis, document drafting and scheduled jobs; Code Mode supports remote coding sessions, parallel runs and sandbox isolation, along with a VS Code extension and an updated CLI.

    Why it matters: The official announcement fully covers Vibe's Work and Code modes, pricing and access points, letting readers assess its impact on daily workflows and coding processes.

May 22Fri
  1. Mistral AI70

    Remote agents in Vibe. Powered by Mistral Medium 3.5.

    Mistral released the 128B open-weight flagship model Mistral Medium 3.5 (public preview), combining instruction following, reasoning and coding, with a 256k context window and a SWE-Bench Verified score of 77.6%. API pricing is $1.5 per million input tokens and $7.5 per million output tokens.

    Why it matters: The original provides model specs, benchmark scores, pricing and the open-weight access point, useful for evaluating it for self-hosting and asynchronous coding use cases.

May 20Wed
  1. Google Research62

    Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery

    Google's research tool ERA uses Gemini to write and optimize scientific code, and the related paper was published in Nature today. ERA uses tree search to consider thousands of approaches and reaches expert-level performance on benchmarks in genomics, public health, satellite imagery, neuroscience, time series forecasting, and mathematics.

    Why it matters: The article gives ERA's performance on benchmarks across multiple disciplines and eight application cases, letting readers understand how AI-assisted scientific computing is actually being deployed.

May 16Sat
  1. Google DeepMind84

    Gemini 3.5: frontier intelligence with action

    Google DeepMind has released the Gemini 3.5 model family, starting with 3.5 Flash, positioned for agents and coding. It outperforms Gemini 3.1 Pro on Terminal-Bench 2.1 (76.2%), GDPval-AA (1656 Elo), MCP Atlas (83.6%), and CharXiv Reasoning (84.2%), with output speed 4x that of other frontier models.

    Why it matters: The official release shares 3.5 Flash's benchmark scores, availability channels, and plans for a Pro follow-up, letting readers evaluate its trade-offs for agent and coding workloads.

May 6Wed
  1. Google DeepMind67

    AlphaEvolve: How our Gemini-powered coding agent is scaling impact across fields

    Google DeepMind has released a one-year impact report on AlphaEvolve, the Gemini-powered coding agent that has expanded from pilots to multiple research and commercial domains.

    Why it matters: The official report details AlphaEvolve's concrete results and figures across research and commercial settings over the past year, showing the real-world reach of this kind of algorithm-discovery agent.

May 4Mon
Mar 31Tue
Mar 25Wed
Mar 17Tue
Mar 11Wed
Jan 28Wed
  1. Mistral AI64

    Terminally online Mistral Vibe.

    Mistral has released Mistral Vibe 2.0, upgrading its terminal-native coding agent, powered by the Devstral 2 model family. New features include custom subagents, multi-option clarification before execution, slash commands to load skills, a unified Agent mode, and auto-updates.

    Why it matters: The article details Vibe 2.0's features, subscription plans, and Devstral 2 API pricing, so readers can evaluate whether to switch their coding workflow.

Dec 9Tue
  1. Mistral AI72

    Introducing: Devstral 2 and Mistral Vibe CLI.

    Mistral AI has released the open source coding model family Devstral 2, comprising the 123B Devstral 2 (modified MIT license) and the 24B Devstral Small 2 (Apache 2.0). Both support 256K context windows and score 72.2% and 68.0% on SWE-bench Verified respectively.

    Why it matters: The official post covers both models' open source licenses, SWE-bench Verified scores, API pricing, and hardware requirements, so readers can assess local or on-device deployment feasibility.

Jul 30Wed
Jul 11Fri
Jun 4Wed
May 28Wed
  1. Mistral AI56

    Codestral Embed

    Mistral AI has released Codestral Embed, its first code-specific embedding model, claiming it outperforms Voyage Code 3, Cohere Embed v4.0, and OpenAI's large embedding model on real-world code retrieval.

May 21Wed
  1. Mistral AI69

    Devstral

    Mistral AI and All Hands AI have launched Devstral, an agentic large language model for software engineering tasks, released as open source under the Apache 2.0 license.

    Why it matters: The official release includes model weights, API pricing, specific SWE-Bench Verified scores and deployment requirements, letting readers assess fit for local or enterprise coding scenarios.

May 7Wed
  1. Mistral AI64

    Medium is the new large.

    Mistral AI released Mistral Medium 3, positioned as a new class of model with SOTA performance at 8x lower cost. It reaches or exceeds 90% of Claude Sonnet 3.7 on benchmarks, is priced at $0.4 input / $2 output per M token, surpasses Llama 4 Maverick and Cohere Command A, and can be self-deployed on 4 or more GPUs.

    Why it matters: The official release provides benchmarks against Claude Sonnet 3.7, pricing, and deployment requirements, letting readers evaluate its cost-effectiveness for enterprise adoption.