jnstrdm05
Re:Mathematics has changed. Let's act like it
on Sunday November 01, 2026 @01:57PM (#50328514)
But in a human way? I don't think so. The 700+ solutions that were put out by openAI are in no way accepted as solved until humans say so. It's kind of like saying SC2 was solved when Alpha beat the best players. The professional community just went on playing much the same. Math should do the same. Just with better tools
Re:Go LLM SDK for streaming, tool-calling AI backends (plus frontend R...
on Thursday July 30, 2026 @09:49AM (#49110014)
Very nice! Thanks for putting this out there
Re:PostHog Open Sourced
on Thursday July 09, 2026 @11:42AM (#48847773)
I just recently switched to posthog self hosted and it works fine
Re:Launch HN: Freestyle: Sandboxes for AI Coding Agents
on Monday April 06, 2026 @02:12PM (#47664666)
how many seconds to provision are we talking about here? 1 sec vs 60 is a dealbreaker for me, some clarity on that would be nice.
Re:Show HN: Antfly: Distributed, Multimodal Search and Memory and Grap...
on Tuesday March 17, 2026 @12:25PM (#47414873)
This looks sick!
Did you build this for yourself?
Re:Show HN: Timber – Ollama for classical ML models, 336x faster than ...
on Sunday March 01, 2026 @09:40PM (#47213239)
I have been waiting for this! Nice
Re:I made MCP cheaper
on Thursday February 26, 2026 @09:48AM (#47166853)
The guy who created fastmcp, he mentioned that you should use mcp to design how an llm should interact with the API, and give it tools that are geared towards solving problems, not just to interact with the API. Very interesting talk on the topic on YouTube. I still think it's a bloated solution.