Description
More from Hacker
Show HN: Open-source alternative to ChatGPT Agents for browsing
Show HN: Open-source alternative to ChatGPT Agents for browsing Hey HN,<p>We are Winston, Edward, and James, and we built Meka Agent, an open-source framework that lets vision-based LLMs execute tasks directly on a computer, just like a person would.<p>Backstory:<p>In the last few months, we've been building computer-use agents that have been used by various teams for QA testing, but realized that the underlying browsing frameworks aren't quite good enough yet.<p>As such, we've been working on a browsing agent.<p>We achieved 72.7% on WebArena compared to the previous state of the art set by OpenAI's new ChatGPT agent at 65.4%. You can read more about it here: <a href="https://github.com/trymeka/webarena_evals">https://github.com/trymeka/webarena_evals</a>.<p>Today, we are open sourcing Meka, our state of the art agent, to allow anyone to build their own powerful, vision-based agents from scratch. We provide the groundwork for the hard parts, so you don't have to:<p>* True vision-based control: Meka doesn't just read HTML. It looks at the screen, identifies interactive elements, and decides where to click, type, and scroll.<p>* Full computer access: It's not sandboxed in a browser. Meka operates with OS-level controls, allowing it to handle system dialogues, file uploads, and other interactions that browser-only automation tools can't.<p>* Extensible by design: We've made it easy to plug in your own LLMs and computer providers.<p>* State-of-the-art performance: 72.7% on WebArena<p>Our goal is to enable developers to create repeatable, robust tasks on any computer just by prompting an agent, without worrying about the implementation details.<p>We’d love to get your feedback on how this tool could fit into your automation workflows. Try it out and let us know what you think.<p>You can find the repo on GitHub and get started quickly with our hosted platform, <a href="https://app.withmeka.com/" rel="nofollow">https://app.withmeka.com/</a>.<p>Thanks, Winston, Edward, and James
Show HN: The Montana MiniComputer
Show HN: The Montana MiniComputer Hey HN, we just released the 1.0 of the MonTana Mini Computer (MTMC-16), a virtual teaching computer to help students understand how low level computing works. It is a 16 bit computer with only 4k of ram, but we've made some design choices that help maximize what you can accomplish with the limited hardware<p><a href="https://mtmc.cs.montana.edu/" rel="nofollow">https://mtmc.cs.montana.edu/</a><p>It is written in java (sorry) and provides a web interface that has:<p>- a blinken-lighten display for registers<p>- a memory view with different filters you can apply<p>- a Gameboy-like game pad<p>- a console you can use to interact with the computer (including running assembly instructions directly)<p>- a file browser with an integrated editor for editing file<p>So everything you need to get going on low level programming.<p>It includes some sample code, including snake and conway's game of life, in the /src directory.<p>You can watch a quick start video here: <a href="https://www.youtube.com/watch?v=m_6pZ_sT3y0" rel="nofollow">https://www.youtube.com/watch?v=m_6pZ_sT3y0</a><p>We have the start of a C compiler for the machine, but that's still a work in progress. We plan on improving the interactivity and visual feedback over the next few months, so any feedback you can give us would be very much appreciated!
A fast 3D collision detection algorithm
A fast 3D collision detection algorithm I discovered this collision detection algorithm during COVID and finally got around to writing about it.<p>github repo: <a href="https://github.com/cairnc/sat_blog">https://github.com/cairnc/sat_blog</a>
No other tools from this source yet.