标签：#hack

I run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" ( https://transformer-circuits.pub/2026/workspace/index.html ) It talks about how they use a tool they call a Jacobian Lens to view inside the middle layers of LLM while it's working before it commits to a word (token). I wanted to see if I could get a version of this running on the open models and to my surprise it worked! I ran some experime

https://deploymentsafety.openai.com/gpt-5-6/gpt-5-6.pdf https://developers.openai.com/api/docs/guides/latest-model

Devthropology is a passion project built on top of GitHub pull data. The name is a play on developer anthropology. Pull request data can be cut a lot of ways. The functionality has been built out of curiosity as I want to see different insights into codebases that I work on. Some of the data is typical and other parts I haven't seen elsewhere. I think of this as an improved GitHub Insights page, with faster performance, more detail, and a focus on how work moves through a codebase. The main enti

Hey HN! We built a browser-based agent that runs inside an authenticated web app, watches how the app calls its own APIs, and automatically turns those into agent tools. You can think of it as an auto-generated MCP server that self-updates as the host app changes. The result is a skilled AI assistant that actually integrates deeply with any product (not just chat and RAG) with minimal effort. Check out these short demos below that show the agent in software you're probably familiar with: - Jira:

We're open-sourcing Sighthound today, our rules-based static security scanner. What makes it special is that it's coded in rust and uses tree-sitter as it's AST making it very fast and easily extensible. Why build another scanner in 2026? We wanted to improve some of our detection outcomes but noticed the current open source scanners like Semgrep/Opengrep we're capped by a bunch of adoption limitations such as being written in OCaml, requiring a lot of work to add a language parser, and the rule

Hi Hacker News, I’m Yahia. I built Context.dev ( https://www.context.dev/ ) to make it really easy to integrate web data into your products and agents. Here’s a demo video: https://www.tella.tv/video/build-faster-with-context-dev-api... Since it’s an API, here are the docs: https://docs.context.dev/quickstart . You can send us a URL and get back clean Markdown, rendered HTML, screenshots, extracted images, etc.. You can also send us a domain and get company or brand context: name, description, l