News for hackers. Stuff that matters.

0xchamin

page not available for me.
Re: on Monday July 13, 2026 @03:02PM (#48897212)
If you like to think from foundations, I believe this video will give a great overview on "Harness Engineering"
Re:Show HN: Eyeball on Thursday June 04, 2026 @08:06AM (#48397490)
cool game. I tried. would be nice to include a helper description around what to do. took me a while to understand the challenge better.
I enjoy learning the fundamentals right. This article, and the series follow, by an engineer from OpenAI engineer, dive deep into the fundamentals. Sharing in HN because it might help others too. If you happen to know other fundamental articles, please do share.
Re:Google Plans to Invest Up to $40B in Anthropic on Saturday April 25, 2026 @12:55PM (#47902820)
circular economy???
One of the biggest problem with Claude is, it tries to do things that I don't even ask. I really like to have full control over what I do. I feel sometimes, Claude has the urgency to keep going with what it is hardcore programmed for instead waiting for my feedback. Looks like, Claude consider everything to be oneshot. I maybe wrong, this is my personal experience

Show HN: Interactive knowledge graph for the AAuth (Agent Auth) protocol

https://mcp-shark.github.io/aauth-explorer/

I built a graph explorer for AAuth (Agent Auth) — an exploratory IETF draft from Dick Hardt (OAuth 2.0 author, 2.1 co-author) where every agent has its own cryptographic identity, with no pre-registration and no bearer tokens. Every request is signed; tokens are key-bound.The official Explorer at https://explorer.aauth.dev is scenario-oriented. This is a complementary view — the whole protocol...

( Read More... | no comments | on HN )
I use Claude Code and Gemini and to LLM as a judge among the two to review each others result and generate a final mermiad diagram.
very interesting. Prompt to "generate System Design like ChatGPT end to end". Took about ~3-5 mins the model to download. It generated a reasonably good system design.
Re:How to implement cryptographically-secure API keys on Wednesday April 15, 2026 @04:58AM (#47776445)
curious, does this highlight open standards?
great suggestion. I can add that to road map.
Re:Show HN: Continual Learning with .md on Tuesday April 14, 2026 @05:36AM (#47763311)
is this based on Karapathy's LLM Wiki idea (link: https://gist.github.com/karpathy/442a6bf555914893e9891c11519...)? . I leveraged Karapathy's wiki idea and built MCPTube- it's a CLI and also an MCP server that turns YouTube videos into a compounding knowledge base. Check it out and let me know what you think (link: https://github.com/0xchamin/mcptube)
Re:The tech jobs bust is real. Don't blame AI (yet) on Monday April 13, 2026 @07:46PM (#47759439)
One of my mentor at my company got redundant exactly a year ago. He is still looking for the next role. I really feel bad.

Show HN: Mcptube – Karpathy's LLM Wiki idea applied to YouTube videos

https://github.com/0xchamin/mcptube

I watch a lot of Stanford/Berkeley lectures and YouTube content on AI agents, MCP, and security. Got tired of scrubbing through hour-long videos to find one explanation. Built v1 of mcptube a few months ago. It performs transcript search and implements Q&A as an MCP server. It got traction (34 stars, my first open-source PR, some notable stargazers like CEO of Trail of Bits).But v1...

( Read More... | 3 comments | 2 points | on HN )
done. good luck!