2026-10-13 AI 日报

Reverse engineer anything with agents, from app behavior down to native binaries.

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via…

Write HTML. Render video. Built for agents.

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image…

Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No…

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is…

AirLLM 2.8T LLM inference with single 4GB GPU

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus…

Give your agents the power to publish reviewable HTML documents. Self-hosted server + CLI + remote MCP; agents push, humans review with comments and versions.

Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast…

As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own…

Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention. We study…

Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view…

Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool…

Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth…

Video interactive storytelling enables viewers to actively steer how a video unfolds. However, once we allow viewers to intervene during generation, a new…

Personal Graphical User Interface (GUI) agents rely on interaction history to infer what a user wants from ambiguous instructions and to anticipate recurring…

When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and mentally reconstruct the spatial…

Historical street-view imagery records urban evolution, but uneven coverage leaves substantial gaps in historical records. Generating plausible past…

At Anthropic, coding is no longer the bottleneck to building systems or doing research. Claude is able to autonomously iterate on research loops,…

See also: Gemini 4 Argon for Robotics - https://news.ycombinator.com/item?id=50074869

https://x.com/OpenAINewsroom/status/2110095403198849132

Main thread: Gemini 4 Argon - https://news.ycombinator.com/item?id=50073879

Hi HN, I'm Niz. Pulse Local is a budgeting app for Mac (Apple Silicon, beta) that answers questions about your spending with models that run on your machine.…

Existing benchmarks measure solve rate and token output/cost, but don't punish excess code, which makes a codebase harder to work with in the long term. I…

New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000…

The moment you've been waiting 4… Our new frontier model, Gemini 4 Argon, is rolling out now in the Gemini app to bring your most complex ideas into reality.…

Gemini 4 Argon is now globally available. Built to solve your hardest problems from start to finish, the model brings frontier capabilities across coding,…

https://t.co/oADallGYuR

Try the Supabase plugin in @bot to monitor, debug, and ship changes to your backend

We discovered a sophisticated recording device that was hidden inside one of our offices. We used our models to understand the device and where it had come…

Holy shit I just got our entire company's Claude Enterprise account suspended 😭 https://t.co/Xr1DEyRWb7

Anthropic annonces internal Scion replacing git

They reveal many things they didn't have to. For example...how valuable, exactly, is the raw (encoded) reasoning, vs the summarized reasoning the user sees?…

All seems a bit pointless now. Either pump out AI papers and neglect your own development, or take it slow and fall behind in the publishing race. I already…

We’re giving developers, enterprises, scientists, and consumers access to Gemini 4 Argon, our latest frontier model.

GPT‑6 is rolling out globally in ChatGPT with Intelligent UI, delivering faster responses with visuals and interactive experiences you can explore and use…

Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud…

Illicit distillation allows model developers to copy frontier AI capabilities without creating proportionally robust safeguards. Here, we describe how we’ve…

text-to-image

Our experiments suggest that small AI models may be only months away from being capable enough to self-replicate on commercial IoT devices, like Android TVs…

Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.

automatic-speech-recognition

text-classification