ccch1mneyyy/dsh-Go
dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。
Signal over noise
A ranked view of AI, software, research, and tools from primary sources and technical communities.
Updated
Top signal
Ranked from the last 36 hours
dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。
The OpenAI science blog shares new findings, practical methods, and firsthand accounts from researchers using AI to advance scientific discovery.
Explore a candidate nonperturbative lattice definition of the Standard Model and how GPT-6 Astra helped turn the idea into a detailed proof.
While awkward, creepy tech executives have become a recurring theme on Saturday Night Live, this week’s episode gave the cast a chance to show off all their impressions at once.
"Jensen is Nvidia, right? And so much of this economy is riding on Nvidia."
Comments
Changes since langchain-mistralai==1.1.6 fix(mistralai): fix streaming behavior for reasoning models ( #41887 ) fix(groq,mistralai,xai): bump deps ( #41884 ) chore(model-profiles): refresh model profile data ( #41861 ) release(mistralai): 1.2.0 ( #41859 ) feat(mistralai): route ChatMistralAI through LangSmith gateway ( #41840 ) chore(model-profiles): refresh model profile data ( #41828 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(deps): patch newer-python security lock resolutions ( #41585 ) chore(model-profiles): refresh model profile data ( #41573 ) chore(model-profiles): refresh model profile data (…
Changes since langchain-groq==1.1.3 fix(groq): specify reasoning_effort in integration tests ( #41886 ) fix(groq,mistralai,xai): bump deps ( #41884 ) release(groq): 1.2.0 ( #41856 ) feat(groq): route ChatGroq through LangSmith gateway ( #41837 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(model-profiles): refresh model profile data ( #41432 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(model-profiles): refresh model profile data ( #41354 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/groq ( #41386 ) fix: fix dependencies in some partner packages (…
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Hacker News
Ranked by community signal, then daily relevance
Comments
Hey HN readers! I'm snipedbywifi ( https://gitlab.com/snipedbywifi ), and i've been working on terminactory. Please try it out if you'd like to play a cozy factory game while waiting for long agent tasks to finish! The game is a factory game (overused niche, i know xD), but runs in your terminal. Reason i built it? glad you asked: So basically, it started off with me wanting a terminal-native factory game. Me and the modern 5.5 claude models made a base for the game that I liked, and then i went ham adding features / fixing some minor flaws (like adding claude code hooks so you recieve "telegrams" [the agent's responses], so you can review…
Changes since langchain-mistralai==1.1.6 fix(mistralai): fix streaming behavior for reasoning models ( #41887 ) fix(groq,mistralai,xai): bump deps ( #41884 ) chore(model-profiles): refresh model profile data ( #41861 ) release(mistralai): 1.2.0 ( #41859 ) feat(mistralai): route ChatMistralAI through LangSmith gateway ( #41840 ) chore(model-profiles): refresh model profile data ( #41828 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(deps): patch newer-python security lock resolutions ( #41585 ) chore(model-profiles): refresh model profile data ( #41573 ) chore(model-profiles): refresh model profile data (…
Changes since langchain-groq==1.1.3 fix(groq): specify reasoning_effort in integration tests ( #41886 ) fix(groq,mistralai,xai): bump deps ( #41884 ) release(groq): 1.2.0 ( #41856 ) feat(groq): route ChatGroq through LangSmith gateway ( #41837 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(model-profiles): refresh model profile data ( #41432 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(model-profiles): refresh model profile data ( #41354 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/groq ( #41386 ) fix: fix dependencies in some partner packages (…
Changes since langchain-deepseek==1.1.1 release(deepseek): 1.2.0 ( #41858 ) feat(deepseek): route ChatDeepSeek through LangSmith gateway ( #41839 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/deepseek ( #41389 ) chore(model-profiles): refresh model profile data ( #41325 ) chore(model-profiles): refresh model profile data ( #41283 ) fix: fix dependencies in some partner packages ( #41266 ) chore(deps): bump urllib3 from 2.7.0 to 2.8.0 in /libs/partners/deepseek ( #40962 )…
Changes since langchain-core==1.8.0 release(core): 1.8.1 ( #41855 ) chore(deps): bump soupsieve from 4.0 to 4.1 in /libs/core ( #41850 ) feat(core): per-context LangSmith gateway override via langsmith_gateway ( #41836 ) chore(deps): bump soupsieve from 2.9 to 4.0 in /libs/core ( #41833 )
Author here. I have been reading papers and taking notes for years, using Zotero for the PDFs, Obsidian for the notes, and, recently, an AI chat tab for my questions. Gamma PDF is my attempt to make that one place. In Gamma, you open a paper by simply pasting an arXiv (or DOI) link. Highlight a sentence, or drag a box round a figure, and it becomes a note beside the page with the quote and a link back. You can ask the AI about a figure or some text, and you get an answer that cites a page you can click. You can read and annotate papers on an iPad with the Apple Pencil. Notability (Goodnotes) import/export is supported. You can connect to…
Release Notes [2026-11-13] llama-index-agent-agentmesh [0.3.0] Python security relock: all integration uv.lock files (lock files only, no Python floor changes) ( #24039 ) BREAKING: raise requires-python for security fixes across integrations (stacked on #24039 ) ( #24040 ) llama-index-callbacks-argilla [0.6.0] Python security relock: all integration uv.lock files (lock files only, no Python floor changes) ( #24039 ) BREAKING: raise requires-python for security fixes across integrations (stacked on #24039 ) ( #24040 ) llama-index-callbacks-arize-phoenix [0.8.0] Python security relock: all integration uv.lock files (lock files only, no Python…
Changes since langchain-xai==1.3.0 fix(groq,mistralai,xai): bump deps ( #41884 ) release(xai): 1.4.0 ( #41857 ) feat(xai): route ChatXAI through LangSmith gateway ( #41838 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(model-profiles): refresh model profile data ( #41651 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(deps): bump aiohttp from 3.14.4 to 3.14.5 in /libs/partners/xai ( #41374 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/xai ( #41371 ) chore(deps): bump aiohttp from 3.14.3 to 3.14.4 in /libs/partners/xai ( #41361 ) chore(model-profiles):…
Hey HN! I'm Lakshay. Raveen and I have built Cerulion, a ROS2-compatible robotics runtime written in Rust. We've worked hard on lowering IPC transport latencies without making the single process tradeoff or forcing POD message types. These fast multi-process graphs can then be resimmed deterministically, and existing ROS2 nodes/launch files can run unmodified alongside native Cerulion Rust/Python code. Installation and quickstart (with a one-shot prompt for your favorite coding agent) here at the repo README: https://github.com/cerulion-inc/cerulion I worked on off-road autonomy during my PhD at MIT, and we kept running into inter-process…
We (GREP.AI, YC F26) are open-sourcing AgentRun and turning it into a full managed agents platform. Read more about it in this post: https://agentrun.ai/blog/introducing-agentrun-run-smarter-ag... . It includes what we originally built for our own agent harness: - Self-improving agents - Web-grounded workflows - A range of sandboxes and computer environments - Thousands of tools and integrations - Detailed analytics on how your agents behave You can bring your own agent. AgentRun works with Pi, Claude Agents, Codex, OpenCode, and any other harness that supports ACP. You can self-host it (see 1-click install on Render) with an OpenRouter key,…
Hey HN! We're Alireza and Majid building Leeroo ( https://leeroo.com/ ). Previously we’ve built AI systems for products with millions of users, including at LinkedIn and Meta. We’re now focusing on building AI systems for enterprise data. Today, we're open-sourcing Kapso ( https://github.com/Leeroo-AI/kapso ), an engine that runs experiments, deploys the best solution, and learns from every run. The nature of data work is iterative: investigate, form hypotheses, experiment, and improve based on what you learn. This bottom-up process is the only way to deliver meaningful outcomes quickly in large, messy enterprise data environments.…
Release candidate for 1.0.3. Install it explicitly: pip install 'browser-use==1.0.3rc1' . Plain installs still get 1.0.2. --cli-mcp exits cleanly when the client closed the pipe before the reply. The CLI runs its own Chromium when no browser has remote debugging on or there is no display. A BU_CDP_URL nothing listens on fails in 3 s with one clear message. Chrome in another pid namespace (containers, Cursor on Linux) is accepted via its DevToolsActivePort. A cancelled cloud run copies downloads within 10 s instead of holding the browser up to 300 s per pass. ActionResult drops and warns about every ignored 0.x field, not only the first (…
I've been developing applications for a long time and have turned to game development as well lately. One of the things that frustrated me the most was that using AI agents for game development is very annoying in the art department. Your only options right now are to either use an image genAI model and roll the dice every time you want to make an edit, or have your agent draw with something like vectors. I was looking for an application that would allow me to ask an agent to make a first draft of whatever art I needed with actual brushes, and then be able to go in myself and edit every last stroke or layer that it created. Klad is that…
Hey HN, I’m Eric and I want to share an OSS project that I’ve been building in my free time. Yogurt is a free, MIT licensed desktop app that uses on-device AI models to transcribe, summarize, and chat with your meetings. Here's a quick demo video: https://www.youtube.com/watch?v=BFfbXAwRq98 Similar to Granola, Yogurt runs in the background and does not join your calls. But unlike Granola, Yogurt is open-source, free to use, and private. Your meeting transcripts, call recordings, and summaries never leave your computer. As small OSS models have gotten faster and more powerful, Yogurt seemed like a pretty obvious win for privacy and cost…
Hi HN, Llmtee is a lightweight llm proxy. I built this project because I needed a simple way to log llm calls across my agents. Existing options require running Postgres, ClickHouse and Redis, or have me use an SDK. llmtree is just a single binary. You point your provider base url to llmtee, it will pass the traffic through chunk by chunk and log the usage to an SQLite database (or optionally Postgres). The container image is ~25 MB. Memory footprint is around ~40 MB and added latency is ~0.2 ms.
pip install 'browser-use==1.0.3' --cli-mcp exits cleanly when the client closed the pipe before the reply (was exit 1 with ExceptionGroup ). The CLI runs its own Chromium when no browser has remote debugging on or there is no display, like --cli-mcp . It persists across calls; browser-use --reload closes it. A BU_CDP_URL nothing listens on fails in 3 s with one message naming the value and both ways out (was a 30 s wait). Chrome in another pid namespace (containers, Cursor on Linux) is accepted via its DevToolsActivePort. A cancelled cloud run copies downloads within 10 s instead of holding the browser up to 300 s per pass. ActionResult drops…
GitHub
Recent AI repositories ranked by growth and activity
dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。
An on-device AI agent for Android that operates apps and the web to get things done for you.
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Education Innovation
Health & Bioscience
Predicting how DNA sequences and their variations impact specific human cell types and disease.
Microsoft researchers have discovered “Lazarus,” a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears. The threat is especially serious for AI agents with tool or terminal access. A triggered model could quietly download and run attacker code, […] The post Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents appeared first on Microsoft Research .
AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.
Foundational precipitation and geostationary satellite datasets to observe the planet clearly.
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
Health & Bioscience
AI agents can generate code at a scale that’s hard for humans to review line-by-line. PDD Kit helps ensure the code is doing what the developer intended by creating formal specifications and testing against them. It converts developer intent into a Verus specification, proves AI-generated code meets it for every input, and uses tests where proofs aren't practical. Developers review intent, not every line. The post Formally verifying agent-written full-stack web apps with PDD Kit appeared first on Microsoft Research .
Data Mining & Modeling
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
Evaluating Microsoft Copilot at enterprise scale requires test data that captures the full complexity of real organizations, yet real enterprise data contains sensitive information that cannot be used for evaluation under any circumstances. The post From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence appeared first on Microsoft Research .
Education Innovation
Generative AI
Health & Bioscience
Comments
Comments
Changes since langchain-mistralai==1.1.6 fix(mistralai): fix streaming behavior for reasoning models ( #41887 ) fix(groq,mistralai,xai): bump deps ( #41884 ) chore(model-profiles): refresh model profile data ( #41861 ) release(mistralai): 1.2.0 ( #41859 ) feat(mistralai): route ChatMistralAI through LangSmith gateway ( #41840 ) chore(model-profiles): refresh model profile data ( #41828 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(deps): patch newer-python security lock resolutions ( #41585 ) chore(model-profiles): refresh model profile data ( #41573 ) chore(model-profiles): refresh model profile data (…
dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。
Explore a candidate nonperturbative lattice definition of the Standard Model and how GPT-6 Astra helped turn the idea into a detailed proof.
The OpenAI science blog shares new findings, practical methods, and firsthand accounts from researchers using AI to advance scientific discovery.
"Jensen is Nvidia, right? And so much of this economy is riding on Nvidia."
Changes since langchain-groq==1.1.3 fix(groq): specify reasoning_effort in integration tests ( #41886 ) fix(groq,mistralai,xai): bump deps ( #41884 ) release(groq): 1.2.0 ( #41856 ) feat(groq): route ChatGroq through LangSmith gateway ( #41837 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(model-profiles): refresh model profile data ( #41432 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(model-profiles): refresh model profile data ( #41354 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/groq ( #41386 ) fix: fix dependencies in some partner packages (…
Changes since langchain-deepseek==1.1.1 release(deepseek): 1.2.0 ( #41858 ) feat(deepseek): route ChatDeepSeek through LangSmith gateway ( #41839 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/deepseek ( #41389 ) chore(model-profiles): refresh model profile data ( #41325 ) chore(model-profiles): refresh model profile data ( #41283 ) fix: fix dependencies in some partner packages ( #41266 ) chore(deps): bump urllib3 from 2.7.0 to 2.8.0 in /libs/partners/deepseek ( #40962 )…
Comments
Comments
While awkward, creepy tech executives have become a recurring theme on Saturday Night Live, this week’s episode gave the cast a chance to show off all their impressions at once.
An on-device AI agent for Android that operates apps and the web to get things done for you.
Comments
Comments
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Changes since langchain-core==1.8.0 release(core): 1.8.1 ( #41855 ) chore(deps): bump soupsieve from 4.0 to 4.1 in /libs/core ( #41850 ) feat(core): per-context LangSmith gateway override via langsmith_gateway ( #41836 ) chore(deps): bump soupsieve from 2.9 to 4.0 in /libs/core ( #41833 )
Comments
Comments
Comments
Comments
Comments
Comments
Comments
Comments
Comments
Nvidia’s security chief quietly left in August, and now that CEO Jensen Huang has stepped down over his relationships, including one with an executive at a company suspected of funneling chips to China, a former intelligence officer says it’s the kind of leak that runs everyday conversations, which most corporate security teams are poorly equipped to catch.
Release: datasette-llm 0.1a11 datasette-llm is the intermediate plugin for Datasette that supports configuring LLMs for use with other Datasette plugins. This release adds support for OpenAI-compatible endpoints, so you can configure Datasette to use an LLM hosted anywhere that talks the OpenAI pseudo-standard web protocol. This means that if you're running local models with LM Studio or Ollama or llama.cpp (which just hit v1.0.0 ) you can run Datasette via uvx like this: wget https://datasette.io/content.db uvx --with datasette-agent datasette \ --root --secret 1 \ -s plugins.datasette-llm.default_model ' { "model": "lmstudio-qwen",…
The petition had attracted more than 115,000 signatures as of Saturday afternoon.
From Apple's repeatedly delayed Siri AI to OpenAI's messy "super app" launch, here's a look at the AI projects that shut down or missed expectations.
AI applications at the edge often need to run multiple neural networks within limited compute and power budgets. NVIDIA Deep Learning Accelerator (DLA)...
Some governments moved to confirm chip supply commitments, while others are monitoring the impact on local projects or addressing ongoing investigations.
Hey HN readers! I'm snipedbywifi ( https://gitlab.com/snipedbywifi ), and i've been working on terminactory. Please try it out if you'd like to play a cozy factory game while waiting for long agent tasks to finish! The game is a factory game (overused niche, i know xD), but runs in your terminal. Reason i built it? glad you asked: So basically, it started off with me wanting a terminal-native factory game. Me and the modern 5.5 claude models made a base for the game that I liked, and then i went ham adding features / fixing some minor flaws (like adding claude code hooks so you recieve "telegrams" [the agent's responses], so you can review…
Author here. I have been reading papers and taking notes for years, using Zotero for the PDFs, Obsidian for the notes, and, recently, an AI chat tab for my questions. Gamma PDF is my attempt to make that one place. In Gamma, you open a paper by simply pasting an arXiv (or DOI) link. Highlight a sentence, or drag a box round a figure, and it becomes a note beside the page with the quote and a link back. You can ask the AI about a figure or some text, and you get an answer that cites a page you can click. You can read and annotate papers on an iPad with the Apple Pencil. Notability (Goodnotes) import/export is supported. You can connect to…
Teaching a robot to navigate an obstacle course requires more than a walking policy. It must perceive its surroundings, maintain balance, and adjust its actions...
Nvidia poured tens of billions into AI startups under Huang. Without him at the helm, founders and VCs are bracing for smaller checks and lower valuations.
Release Notes [2026-11-13] llama-index-agent-agentmesh [0.3.0] Python security relock: all integration uv.lock files (lock files only, no Python floor changes) ( #24039 ) BREAKING: raise requires-python for security fixes across integrations (stacked on #24039 ) ( #24040 ) llama-index-callbacks-argilla [0.6.0] Python security relock: all integration uv.lock files (lock files only, no Python floor changes) ( #24039 ) BREAKING: raise requires-python for security fixes across integrations (stacked on #24039 ) ( #24040 ) llama-index-callbacks-arize-phoenix [0.8.0] Python security relock: all integration uv.lock files (lock files only, no Python…
Education Innovation
Kitesurf, our experimental browser engine for AI agents, is now open source. Inspect the code, run it locally, or deploy your own instance on Cloudflare Workers.
LangChain now claims 7,000 customers of its model and platform agnostic agent management tool LangSmith.
AI-orchestrated penetration testing platforms like ARTEX have become increasingly powerful tools enabling effective attacks on exposed infrastructure. Here we share Cloudflare’s observations and recommended countermeasures.
New research shows the most advanced AI models from China were trained on banned Nvidia chips.
Researcher traces a path from AI reward hacking to potential human extinction.
Autonomous vehicle (AV) developers need reasoning models that can operate within the compute and latency constraints of an onboard system. Larger models provide...
Changes since langchain-xai==1.3.0 fix(groq,mistralai,xai): bump deps ( #41884 ) release(xai): 1.4.0 ( #41857 ) feat(xai): route ChatXAI through LangSmith gateway ( #41838 ) feat(partners): Remove EOL'd Python 3.10 from partner packages ( #41268 ) chore(model-profiles): refresh model profile data ( #41651 ) chore(infra): relax third-party dependency upper bounds ( #41407 ) chore(deps): bump aiohttp from 3.14.4 to 3.14.5 in /libs/partners/xai ( #41374 ) chore(deps): bump certifi from 2025.8.3 to 2026.10.19 in /libs/partners/xai ( #41371 ) chore(deps): bump aiohttp from 3.14.3 to 3.14.4 in /libs/partners/xai ( #41361 ) chore(model-profiles):…
ChatGPT Wallet lets AI agents shop and check out on users' behalf, starting with a limited rollout to U.S. Pro subscribers.
Jensen Huang has resigned from Nvidia following an affair, which could have ramifications for national security as the U.S. and China race to develop the most advanced AI infrastructure.
Introducing ChatGPT Wallet, a secure way for agents in ChatGPT Work, Codex, and dots to complete purchases with user approval and existing card protections.
ElevenAI is a new meeting notetaker and dictation app aimed at teams and enterprises.
Spend Management adds opt-in spending caps for Cloudflare Workers and Durable Objects, and more products soon. Here is how we built the metering pipeline that turns usage into runtime decisions.
Given Nvidia’s stronghold on AI and its importance in Israel, many in the country's startup ecosystem are worried about the impact of his departure.
Huang described Kress as a "deer in the headlights" during a meeting in summer.
After my last trash clock ( https://news.ycombinator.com/item?id=49930439 ), I wanted to see how low I could go. My latest clock is built mainly from empty drink cartons, plus a few skewers, some paper straws, a piece of string, some nuts as weights, and lots of hot glue. It has a pendulum, an escapement, and hands for seconds, minutes, and hours, and runs for about an hour. The design of the gears and escapement was AI-assisted: Claude built me interactive browser tools that generate templates and 3D-printable jigs and tools. I’m happy to answer your questions! And to the commenter who suggested I submit trash clock timekeeping as a talk to…
Shield uses OpenAI to help IT technicians hand off work in legacy portals. Its Forge agents navigate systems so technicians can focus on issues needing their judgment.
This Congressional investigation into Nvidia's China sales and its dealings with Trump is the second one, so far, since news of the alleged spy affair broke.
Running a frontier-scale model locally means keeping all its weights in GPU memory; the largest models no longer fit on one machine. Two NVIDIA DGX Stations...
https://twitter.com/willdepue/status/2120992457630326841
Hey HN! I'm Lakshay. Raveen and I have built Cerulion, a ROS2-compatible robotics runtime written in Rust. We've worked hard on lowering IPC transport latencies without making the single process tradeoff or forcing POD message types. These fast multi-process graphs can then be resimmed deterministically, and existing ROS2 nodes/launch files can run unmodified alongside native Cerulion Rust/Python code. Installation and quickstart (with a one-shot prompt for your favorite coding agent) here at the repo README: https://github.com/cerulion-inc/cerulion I worked on off-road autonomy during my PhD at MIT, and we kept running into inter-process…
Representatives from Nvidia told Illinois representative Bill Foster that it would be technically possible to implement the anti-smuggling measures called for in the Chip Security Act, Foster told MIT Technology Review in an interview on Thursday, even while an industry group claimed they were “potentially infeasible.” Foster, a Democrat who serves on the Committee on…
Built primarily on OpenAI models, Amplitude’s proactive product agent, Wave, identifies what to build, helps teams ship changes with coding agents, and measures the impact.
Families confront Google after teen’s lawsuit labels Gemini a “suicide coach.”
We (GREP.AI, YC F26) are open-sourcing AgentRun and turning it into a full managed agents platform. Read more about it in this post: https://agentrun.ai/blog/introducing-agentrun-run-smarter-ag... . It includes what we originally built for our own agent harness: - Self-improving agents - Web-grounded workflows - A range of sandboxes and computer environments - Thousands of tools and integrations - Detailed analytics on how your agents behave You can bring your own agent. AgentRun works with Pi, Claude Agents, Codex, OpenCode, and any other harness that supports ACP. You can self-host it (see 1-click install on Render) with an OpenRouter key,…
Hey HN! We're Alireza and Majid building Leeroo ( https://leeroo.com/ ). Previously we’ve built AI systems for products with millions of users, including at LinkedIn and Meta. We’re now focusing on building AI systems for enterprise data. Today, we're open-sourcing Kapso ( https://github.com/Leeroo-AI/kapso ), an engine that runs experiments, deploys the best solution, and learns from every run. The nature of data work is iterative: investigate, form hypotheses, experiment, and improve based on what you learn. This bottom-up process is the only way to deliver meaningful outcomes quickly in large, messy enterprise data environments.…
Gondola helps creatives get credit and get hired, with Codex raising its lead engineer’s output by 50% and ChatGPT simplifying daily work.
With Codex, Holiday Extras is turning customer expertise into better apps, higher booking conversion and new possibilities for growth.
Release candidate for 1.0.3. Install it explicitly: pip install 'browser-use==1.0.3rc1' . Plain installs still get 1.0.2. --cli-mcp exits cleanly when the client closed the pipe before the reply. The CLI runs its own Chromium when no browser has remote debugging on or there is no display. A BU_CDP_URL nothing listens on fails in 3 s with one clear message. Chrome in another pid namespace (containers, Cursor on Linux) is accepted via its DevToolsActivePort. A cancelled cloud run copies downloads within 10 s instead of holding the browser up to 300 s per pass. ActionResult drops and warns about every ignored 0.x field, not only the first (…
OpenAI commits $2 million to research on AI and children’s safety. The work supports shared tools to measure risks and opportunities for young people.
A conversation with Sam Nickless, Partner and Chief Executive Officer at Gilbert + Tobin.
Gemini Decisions API Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of questions (yes/no, choice, and rubric-scoring) and even reuses Jev's term "Noul" for a yes/no question. It's priced the same as the GPT-6 Luna decision model: 10 cents per million input tokens, and output is free. Jev remains the cheapest of the three, at 4.2 cents per million. Jev is text (and JSON) only. OpenAI can handle text and images. Gemini Decision 1 is fully multi-model: it covers text, images, audio, video, and PDFs. I tested it against video by…
Health & Bioscience
Browse tools.simonwillison.net by tag I've been wanting a better way to browse my collection of vibe-coded tools (244 and counting) for a while. I had a few Fable 5.2 credits left over before my weekly reset so I set it to work using tree-sitter to analyze the code for JavaScript APIs, libraries, and web API hosts used by each tool. The homepage now features tag clouds for browsing by each of those categories of tag: Tags: javascript , tools , ai , generative-ai , llms , claude , vibe-coding
Latest example of the AI boom’s circular financing comes as AI trade wobbles.
Release: llm 0.37.2 Fixes a security issue reported by Daniel de Araujo in GHSA-v9h7-jj4g-f862 and GHSA-r639-rr7r-x72w . LLM has a mechanism called extra-openai-models.yaml - now managed by the new-in-0.37 llm openai endpoint add command - for using LLM with OpenAI-compatible API endpoints from other providers. Daniel reported two ways this could accidentally send your configured OpenAI API key to one of those providers: if the key named by api_key_name had never been stored, or if a responses: true model was run with -o chat_completions 1 . Tags: projects , security , llm , releases
I've been developing applications for a long time and have turned to game development as well lately. One of the things that frustrated me the most was that using AI agents for game development is very annoying in the art department. Your only options right now are to either use an image genAI model and roll the dice every time you want to make an edit, or have your agent draw with something like vectors. I was looking for an application that would allow me to ask an agent to make a first draft of whatever art I needed with actual brushes, and then be able to go in myself and edit every last stroke or layer that it created. Klad is that…
Hey HN, I’m Eric and I want to share an OSS project that I’ve been building in my free time. Yogurt is a free, MIT licensed desktop app that uses on-device AI models to transcribe, summarize, and chat with your meetings. Here's a quick demo video: https://www.youtube.com/watch?v=BFfbXAwRq98 Similar to Granola, Yogurt runs in the background and does not join your calls. But unlike Granola, Yogurt is open-source, free to use, and private. Your meeting transcripts, call recordings, and summaries never leave your computer. As small OSS models have gotten faster and more powerful, Yogurt seemed like a pretty obvious win for privacy and cost…
Anthropic's IPO roadshow video Anthropic kicked off their IPO roadshow yesterday, and their roadshow video has some previously unreleased information about how their business works. The section on "Approach to compute" with co-founder Tom Brown is particularly interesting, describing how Anthropic train and serve Claude across AWS Trainium, Google TPUs, NVIDIA GPUs, and AMD GPUs. I'm not sure why there's no official video transcript, but here's one that I extracted using MacWhisper. Highlights below: We train and serve Claude now across all four major chip families. That's only possible because early on we made an unconventional bet on a…
Predicting how DNA sequences and their variations impact specific human cell types and disease.
Cloudflare is building an experimental consensus service using a never-before-deployed consensus algorithm, QuePaxa. In this post we explain how QuePaxa works and why we chose it.
The four-week project hints that AI could make formal verification far more practical.
Hi HN, Llmtee is a lightweight llm proxy. I built this project because I needed a simple way to log llm calls across my agents. Existing options require running Postgres, ClickHouse and Redis, or have me use an SDK. llmtree is just a single binary. You point your provider base url to llmtee, it will pass the traffic through chunk by chunk and log the usage to an SQLite database (or optionally Postgres). The container image is ~25 MB. Memory footprint is around ~40 MB and added latency is ~0.2 ms.
More than 20,000 veterans and transitioning service members have claimed a free year of ChatGPT Plus. See how they use it to prepare for civilian careers.
pip install 'browser-use==1.0.3' --cli-mcp exits cleanly when the client closed the pipe before the reply (was exit 1 with ExceptionGroup ). The CLI runs its own Chromium when no browser has remote debugging on or there is no display, like --cli-mcp . It persists across calls; browser-use --reload closes it. A BU_CDP_URL nothing listens on fails in 3 s with one message naming the value and both ways out (was a 30 s wait). Chrome in another pid namespace (containers, Cursor on Linux) is accepted via its DevToolsActivePort. A cancelled cloud run copies downloads within 10 s instead of holding the browser up to 300 s per pass. ActionResult drops…
JioStar’s Vijay Seshadri explains AI discovery at 500M-user scale. Read his lessons on evals, guardrails, and taking AI into production.
No matching items in this view.
Automated index, not original reporting. Ranking uses freshness, source quality, and available community signals. Links point to original sources.