Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: Paste a song and get 5 license-free cousins that sound like it(mockfreeli.org ↗)
    discuss
  2. Show HN: Lightning strike VFX in Three.js, a step-by-step breakdown(threevfx.com ↗)
    discuss
  3. AODM: AI Optimized Data Markup(github.com/fucaspark ↗)
    discuss
  4. There Is No AI Agent(zak.im ↗)
    discuss
  5. Show HN: A toy implementation of ELF relocation weird machines(github.com/scriptod911 ↗)
    discuss
  6. We Need a Way to Prove Personhood Online(noemamag.com ↗)
    discuss
  7. Financial Times – The era of AI warfare has arrived(ft.com ↗)
    discuss
  8. Zuckoff app detects nearby Meta 'perv glasses'(nypost.com ↗)
    discuss
  9. From Specialist Agents to Distributed Skills over MCP(devblogs.microsoft.com/agent-framework ↗)
    discuss
  10. EU president: AI agents escaping their environment preview what's coming(the-decoder.com ↗)
    discuss
  11. Ask HN: How to recover Google auth after phone stolen?
    discuss
  12. A Taxonomy of Toddler Jokes(lastwordonnothing.com ↗)
    discuss
  13. Jev's Architecture Unmasked(archerhume.com ↗)
    discuss
  14. God Eye View(spatialintelligence.ai ↗)
    discuss
  15. Modern Monetary Theory: Economics for the 21st Century (MOOC)(mmted.org ↗)
    discuss
  16. How we made one of our largest inference workloads 4.7× more GPU-efficient(decagon.ai ↗)
    discuss
  17. AI has transformed The Pentagon's aging networks into a national security risk(washingtonpost.com ↗)
    1comments
  18. Show HN: Stroq – trace your agent's commands back to the text that produced them
    2comments
  19. ZSA Backpack(zsa.io ↗)
    discuss
  20. Designing for Amnesia(kasrin.com ↗)
    discuss
  21. Sub-ms deterministic parsing vs. LLM-based policy for agent safety?(github.com/midhunweb ↗)
    discuss
  22. The suddenly explosive world of AI safety(theverge.com ↗)
    discuss
  23. Agentic Societies Need a Social Harness(social-harness.org ↗)
    1comments
  24. We Need a Science of the AI Mind(wsj.com ↗)
    1comments
  25. Iran strikes on Amazon data centers caused permanent loss of customer data(arstechnica.com ↗)
    discuss
  26. Aviation is running telecom's playbook. The year is 1985(marbletech.us ↗)
    discuss
  27. Why Germany Is Building an Ark for U.S. Climate Data(yale.edu ↗)
    discuss
  28. AI model watermarking changes agent behavior(theregister.com ↗)
    discuss
  29. Songs Banned from Radio Following 9/11 Terrorist Attacks(consequence.net ↗)
    discuss
  30. Sloth – passive C99 WiFi SIGINT for Linux, 2,122 tests(github.com/spacetrucker2196 ↗)
    discuss

My AI agent gets his own calendar

9 pointsby 3h agoheyjonny.dev
10 comments
2h agoHN ↗

This is just blogspam, right? The author even brags about hitting the HN front page in such a short amount of time, in a previous post. All he talks about is his agent (that we are supposed to "know"? arrogant). Not a lot of discussion from him about his results.

2h agoHN ↗

Sounds like a natural addition to Agentmail [0]

In general I'd like more services to maintain a wall between me and agent, but then again, we can also let the agents build it.

[0] https://www.agentmail.to/

2h agoHN ↗

That's pretty interesting. There have been a couple of occasions now where I wanted to forward emails to my agent. Going to take a deeper look at that.

56m agoHN ↗

Yeah, I have some boxes with some actions like: match positions in email to my skill set, make top 10, send on Telegram, and one box makes attachments out of emails and forwards to book keeping.

2h agoHN ↗

How does this gratify anyone's intellectual curiosity?

Guy (micro)blogs that his imaginary friend now has a data structure that apparently mimics a calendar and possibly exposes an ical feed.

Good for them, but why does the internet need to know that?

2h agoHN ↗

I found it kinda interesting, even if it could have been written by an AI with extensive prompting on how to sound human.

I've been pondering a conceptually similar approach for keeping slop out of important git repos. The agent has its own slop repo that it can slop up as much as it likes for R&D, and then I transcribe what works into my clean repo (ensuring I understand it, in the process).

2h agoHN ↗

Tbf this is just you - a decent human being that actually has something to say - filling in not just "the blanks" but "the blank". The post of that account trying to build up an identity (see other posts + 0 comments) has nothing to do with that.

One could probably also give you words sampled from /dev/urandom and it might spark an actually interesting thought, but that doesn't give urandom any merit.

FWIW, I've been using a similar workflow as you describe, though the lines have been blurry at times.

2h agoHN ↗

I think you're right, but I also think that some of the best ideas come out of urandom, and the rest is just curation. I didn't find it interesting enough to upvote, but I wouldn't downvote it either.

2h agoHN ↗

urandom has no financial incentive though. It just is. The same can unfortunately not be said about "making it to the HN front page".

But I can see that not everyone is bothered by that as much as I am. Not that I would have any mandate to do so anyway.