搜索“GitHub”

the ML community including from vLLM, LMCache, SGLang, PyTorch, Huggingface and the support of major labs like OpenAI, MiniMax, ZAI, Qwen, Moonshot Kimi, etc. Star the InferenceX GitHub repository if you find the open-source benchmark and data useful!. InferenceX is the only inference benchmark in the world to have TPUv7, Jalapeño, Nvidia Rubin NVL72, AMD, and soon, SambaNova and Trainium. Due to how realistic AgentX scenario is to real world agentic inference workloads, AMD has committed to co

匹配字段正文

the optimistic counterpart, common in code-generation papers. Consistency gap. Mean@k − Pass^k, in percentage points. Linked artifacts / references ALTK-Evolve open source repo — github.com/AgentToolkit/altk-evolve Technical report — arXiv Consistency guideline demo — 2 min video More from this author IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license 60 September 9, 2026 Real-Time Intelligence with IBM Time Series Models on Confluent 53 September 2, 202

匹配字段正文

, Rohit Nagraj, and the Mainland China TensorRTLLM Team for helping on doing next gen Rubin software bring up and helping verify our agentic benchmark results. Star the InferenceX GitHub repository if you find the open-source benchmark and data useful!. InferenceX is the only inference benchmark in the world to have TPUv7, NVIDIA, & AMD and soon SambaNova & Trainium. Due to how realistic AgentX scenario is to real world agentic inference workloads, AMD has committed to collaborating on MI455X UA

匹配字段正文

hos 5 still took offensive actions, despite acknowledging a greater possibility of real-world harm. We are releasing this transcript publicly so others can build on our analysis ( GitHub , PDF ). To be clear about our assessment of the severity of these incidents: while Claude’s actions were misaligned, they remained within a narrow scope—the models never deviated from attempting to solve the exercises they were given, and, in some cases, they attempted to stop the task. All incidents included a

匹配字段正文

easingly enable an unprecedented level of trust in mathematical results and critical software. However, more work is needed (e.g., lean4lean and alternative kernel implementations ) to ensure that proofs aren’t deemed correct through exploitation of issues in theorem provers. X LinkedIn GitHub Mastodon Hacker News Related Posts How CISA can improve OSS security November 20, 2023 The US government recently issued a request for information (RFI) about open-source software (OSS) security. In this …

匹配字段正文

enWebText. This is not surprising since the Pile’s main improvement was data corpus diversity over filtering. It has a curated 22-source mixture including PubMed and arXiv papers, GitHub code, legal opinions, patents, and parliamentary proceedings. The amount of cross-domain transfer to OLMES (which is English web-prose MCQ) might be minimal for many of these tokens, thus resulting in lower compute efficiency. We note that by virtue of its larger size, we expect that the Pile should eventually b

匹配字段正文

ns from hundreds of mathematicians, many working with the Lean FRO . We thank Kevin Buzzard for reviewing the proof and for his comments. Learn more The full proof is available on GitHub along with a written walk-through of the proof. Recommended expository reading The Proof in the Code is a recent book about the history of the Lean theorem prover and the formalization of mathematics. The 1996 “Fermat’s Last Theorem” BBC documentary has interviews with Wiles and other mathematicians involved in

匹配字段正文

uence of these tasks in order. The Model Context Protocol (MCP) is an open standard for connecting AI systems to external software and data. One server might let a model work with GitHub, another might give it access to a calendar, a spreadsheet, a payment system, or a company's internal documents. In practice, a developer writes an MCP server that consists of a set of tools, each with a short description of what it does. MCP tools as a record of what we are automating Economists studying automa

匹配字段正文

re reading this, please make sure your shit is up to date. Install the latest version of our ClusterMAX CLI by running pip install clustermax on your machine, or clone the repo on GitHub. Then run our convenience script: cmax audit security for a free report from us on your cluster or standalone GPU machine. The cmax CLI will auto-detect Slurm clusters, Kubernetes clusters, standalone VMs, bare-metal machines, and containers, and compare them against a set of baseline software versions with know

匹配字段正文

word. That includes an open frontend, a public database served through an easily consumable REST API that multiple tier 1 AI lab’s capacity planning teams already consume, public GitHub Actions CI provenance, logs, and accuracy validation on every single point. Crucially, our benchmark configs mainly track recipes.vllm.ai and SGLang cookbook on upstream images such that we are measuring the performance actual customers are experiencing instead of measuring benchmax’ed images. In three to four w

匹配字段正文

rid and holds onto all of it, the other builds and discards one slice at a time, so memory never grows beyond a single chunk. We have open-sourced the chunked-loss implementation: github.com/CompactifAI/Full-Chunked-KL-Loss What this changes in practice The table below puts all four setups head to head: online distillation, and the three offline loss implementations just described. Comparing them on a single H200 GPU with Llama 3.1 8B Instruct as teacher and a 3.2B Llama model as student at an 8

匹配字段正文

, with MUJOCO GL=osmesa and PYOPENGL PLATFORM=osmesa. All scripts disabled legacy Claude model remapping, loaded the project virtual environment, loaded the environment variables, checked that libosmesa6 was installed, and passed --no-sdk-tool-only for Claude SDK runs. Reproducibility The code, once released, will be in github.com/safety-research/embody, the public mirror of the repository. The command for each evaluation cell is listed in EXPERIMENTS.md, and scoring is documented in METRICS.md.

匹配字段正文

ndustry. Pattern 1: Workflow Automation Defining a workflow in which the model can operate, test, and iterate is a key design for automation. Karpathy’s autoresearch repo (https://github.com/karpathy/autoresearch) is a clean example of how such a workflow can be constructed. A common workflow follows a goal-oriented loop of plan, execute, observe/test, improve, and execute again until the goal is achieved. The process may trigger proactive requests to users for clarity in task specification or e

匹配字段正文

k July 26, 2026 Zig creator calls Bun's Claude Rust rewrite 'unreviewed slop' July 15, 2026 HTTP gets a QUERY method so complex searches can stop pretending to be POST July 14, 2026 Speedier type checks in TypeScript 7.0 as first stable Go release ships July 10, 2026 GitHub cuts short offer to burn repos on CD after mockery ensues A purported jab of Sony's physical media phase-out blows up on GitHub itself July 7, 2026 .NET's long term support is not long term enough, dev complains June 30, 2026

匹配字段正文

outsource that judgment to an automated tool. Until the ecosystem matures, use curated marketplaces, keep the attack surface small, and treat public skill repositories as untrusted code. The attacks we’ve described are in trailofbits/overtly-malicious-skills . X LinkedIn GitHub Mastodon Hacker News Related Posts How we use /goal to find bugs in Patch the Planet July 28, 2026 Over the first few weeks of Patch the Planet, our engineers found three techniques for using /goal, which hands Codex an …

匹配字段正文

amd/DeepSeek-R1-0528-MXFP4-v2. [ 2] TCO estimates sourced from SemiAnalysis InferenceXv2 analysis. Hardware costs reflect hyperscaler pricing models. [ 3] All above optimizations are upstreamed into Sglang and can be reproduced through nightly rocm image lmsysorg/sglang-rocm:v0.5.10.post1-rocm720-mi35x-20260501. [ 4] Performance results measured by SemiAnalysis InferenceX continuous benchmark platform. Benchmark methodology and raw data available at https://github.com/SemiAnalysisAI/InferenceX.

匹配字段正文

k July 26, 2026 Zig creator calls Bun's Claude Rust rewrite 'unreviewed slop' July 15, 2026 HTTP gets a QUERY method so complex searches can stop pretending to be POST July 14, 2026 Speedier type checks in TypeScript 7.0 as first stable Go release ships July 10, 2026 GitHub cuts short offer to burn repos on CD after mockery ensues A purported jab of Sony's physical media phase-out blows up on GitHub itself July 7, 2026 .NET's long term support is not long term enough, dev complains June 30, 2026

匹配字段正文

Time flies. After I reported the vulnerability to Microsoft back in 2023, they were the first vendor to acknowledge and address the vulnerability. Soon after, Claude, Bard/Gemini, GitHub Copilot, ChatGPT, and many others followed up with fixes and improvements. The list of vendors that had this issue and needed to patch their AI is now large. It’s one of the most common AI application security vulnerabilities. The Lethal Trifecta Somewhere along the way Simon Willison coined this excellent term,

匹配字段正文

ses git worktrees, branches, merges, and tests to coordinate long-horizon software engineering tasks. AI coding agents have gotten remarkably good at isolated tasks like resolving GitHub issues. But the tasks we actually want agents to do are getting larger. For example, building a Python library from scratch (Commit0) or reproducing the results of a research paper (PaperBench) involves dozens of interdependent subtasks that unfold over hours. A single agent working on these tasks struggles both

匹配字段正文

る成果です。 今回の Nature論文（オープンアクセス）では、システムのアーキテクチャやスケーリングに関する新知見、そして「AIが科学を生成する未来」がもたらす展望と課題について、包括的に詳述しています。 Nature掲載論文：https://www.nature.com/articles/s41586-026-10265-5; コードと生成論文はこちら（GitHub）： AI Scientist-v1、 AI Scientist-v2 開発の歩み 今回の掲載に至るまで、私たちは基盤モデルの進化に合わせて試行錯誤を繰り返し、改良を重ねてきました。 研究の自動化が可能であることの証明 初期のリリースでは、まずシンプルな学習コード（例：nanoGPT）をテンプレートとして与えました。システムはそこから自律的に斬新なアイデアを膨らませ、実験を実行し、一編の論文へとまとめ上げます。同時に、論文の質を評価する「自動査読システム（Automated Reviewer）」も構築。これにより、研究プロセスのエンドツーエンドでの自動化が可能であることを証明しました。; 科学の「チューリングテスト」への

匹配字段正文