W in le chat

I made code2prompt - A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting. I initially created this tool to leverage Claude 3.0's 200K context window, and it has proven extremely useful, so I am now making it

shipping soon.

Inviting early testers and contributors to Project Devika - The open-source alternative to Devin. 👩‍💻 As of now, Devika is far from the capabilities of Devin... but we'll eventually get there. So I am calling the open-source community to join forces! ❤️ Features: - 12 Agentic

SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-bench, takes 93 seconds on avg + it's open source! We designed a new agent-computer interface to make it easy for GPT-4 to edit+run code github.com/princeton-nlp/…

build and tweet

We've been in the kitchen cooking 🔥 Excited to release the first AI at Meta LLama-3 8B with a context length of over 1M on Hugging Face - coming off of the 160K context length model we released on Friday! A huge thank you to @CrusoeEnergy for sponsoring the compute. Let us know

Founders this is what shipping looks like when you have a vision No memes No interactions with the press Just shipping Pure product Market takeover

guys, we made it yc. small step for stitionAI , huge leap for us. super grateful and thankful for the efforts and help from Anand Krishna , Jijo Sunny, and the ragas team (ikka, Jithin James) thank you! ♥️🚀 mufeed vh Asjid Kalam

YC S24's Asterisk (placeholder) is an AI agent that finds and patches security vulnerabilities in codebases. It can detect business logic errors and generate reports with zero false positives. ycombinator.com/launches/LYC-a… Congrats on the launch, mufeed vh, Vivek R, and Asjid Kalam!

Excited to invest in Asterisk (placeholder) YC S24, an AI agent that finds and patches security vulnerabilities in codebases The AI white hat hackers already hacked 7 open source YC cos Backed by @Ycombinator & Pioneer Fund If you're looking for a complete security audit, let me know!

At Sesame, we believe in a future where computers are lifelike. Today we are unveiling an early glimpse of our expressive voice technology, highlighting our focus on lifelike interactions and our vision for all-day wearable voice companions. sesame.com/voicedemo

Claude reversing a binary using Binary Ninja via MCP while I get a snack blasty Ziyad Edher Vector 35

the CIA is not ready for the RL era israeli intelligence guy just hacked into a live surveillance camera in front of me with an exploit generated by qwen vulnerable software is simulatable. penetration success is verifiable. hacking is RLable.

source code for AIxCC cyber reasoning systems: archive.aicyberchallenge.com

You’re probably using WebViews wrong. There are a million ways to use a WebView wrong. Properly securing a WebView is hard. In this thread, we’ll cover common vulnerabilities in wallet WebView implementations and the ways to properly secure WebViews.

kernel hackers go serverless ring0 → cloud 9 ☁️ ?? brb pwning yr gpu nodes ✨

Now in private beta: Aardvark, an agent that finds and fixes security bugs using GPT-5. openai.com/index/introduc…