News for hackers. Stuff that matters.

rakag

What's the difference between this and OpenWork which has existed for a while?
The codebase is likely entirely AI generated without much review. There are fake "analyses", fake UAV data generated, all the hallmarks of an LLM generating placeholder / dummy data.

    assessment = "ANALYSIS: "

    if any(k in keywords for k in ["strike", "missile", "attack", "bomb", "drone"]):

        assessment += f"{random.randint(75, 95)}% probability of kinetic escalation within 24 hours. Recommend immediate asset relocation from projected blast radius."

    elif...

Lol.
The AI prose is getting so tiring to read

"We measured this. Not estimates — actual token counts using the cl100k_base tokenizer against real schemas, verified by an automated test suite."

Re:Figma's Multiplayer Technology (2019) on Wednesday August 20, 2025 @06:02AM (#44960443)
Haha getting flashbanged halfway through
This is exactly what I need for my project :)

Show HN: We made a local-first LLM assisted journaling tool

https://github.com/re-memo/re-memo

Unsatisfied with the AI journaling tools out there and scared of data leaks, a friend and I made re:memo during a 30 hour hackathon: an LLM assisted journaling app that is designed to run offline!There's still a lot of work to be done, but I've been using it for myself and I'm glad I don't have to send my entire life story to an LLM inference API :)

( Read More... | no comments | on HN )