Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Show HN: Daily updated UI sections and components library(uitopic.com ↗)
    discuss
  2. When an AI Agent Deletes Your Database(obsidiansecurity.com ↗)
    discuss
  3. Tutor-MCP – An adaptive learning engine for any subject(github.com/arnaudguiovanna ↗)
    discuss
  4. Added a reusable retry client to try, thanks to Go 1.27's generic methods(github.com/nodivbyzero ↗)
    discuss
  5. Union Alpha is a multimodal model built for research, coding, agentic workflows(openrouter.ai ↗)
    discuss
  6. Just Prompt, Motherfucker(just-prompt-motherfucker.com ↗)
    1comments
  7. Ask HN: Do you think the software industry has a good culture of whistleblowing?
    discuss
  8. Linjen(headless.design ↗)
    discuss
  9. Can an AI Scientist Start with a Dataset Instead of a Goal?(eamag.me ↗)
    discuss
  10. Zuckerberg on Slowing Down AI(twitter.com/finkd ↗)
    discuss
  11. Show HN: The browser tab as a back end(github.com/ibr0r0 ↗)
    discuss
  12. Why housing reforms keep failing(worksinprogress.news ↗)
    discuss
  13. AI machine 'helps save 25M Lego bricks'(bbc.com ↗)
    discuss
  14. iTorrents.org Compromised to Spread Windows Malware, Kaspersky Says(pcmag.com ↗)
    discuss
  15. Thomson Reuters Built Its Own Legal AI Model(thomsonreuters.com ↗)
    discuss
  16. Magic Statics vs. Std:Call_once(devblogs.microsoft.com/oldnewthing ↗)
    discuss
  17. Europe's Difficult Choices on AI(ft.com ↗)
    discuss
  18. Pixel phones getting Harry Potter ad disguised as theme pack(androidauthority.com ↗)
    discuss
  19. Phone Numberless Registration for Android(signal.org ↗)
    discuss
  20. Build Your Own AI Agent Harness in C#(devblogs.microsoft.com/dotnet ↗)
    discuss
  21. Global chokepoint pressure drives Asia's increased use of Arctic Trade Routes(npr.org ↗)
    discuss
  22. Show HN: I wrote a custom assembler for CHIP-8 in C++(github.com/tackx ↗)
    discuss
  23. Auto SR Comes to Intel Core Ultra Series-3 Processors(devblogs.microsoft.com/directx ↗)
    discuss
  24. Stealth Multimodal AI Model Matches Frontier Performance at a Fraction of Cost(asiaai.fyi ↗)
    discuss
  25. Can AI Build a Toilet Yet?(feelep.xyz ↗)
    1comments
  26. Private memory from meetings you cannot give to the cloud(youtube.com ↗)
    discuss
  27. Google rolls out pay-per-value AI licensing program to publishers(digiday.com ↗)
    discuss
  28. Save the Constitution. Ditch the ABA(uatx.substack.com ↗)
    discuss
  29. The Life Sciences Verification Program(anthropic.com ↗)
    discuss
  30. I got tired of taking screenshots and explaining everything to AI agents(deiko.app ↗)
    1comments

hister

63 pointsby 1h agogithub.com
16 comments
58m agoHN ↗

Integrate it with linkwarden so it searches the bookmarked pages.

20m agoHN ↗

Thanks, that looks interesting, I will test it out and see if it continuously sync or must be manually imported from time to time, or if it can replaces linkwarden entirely. My linkwarden instance also saves as a pdf not just html and bookmarks are in GB in size, if hister does it more efficiently it’s even better.

18m agoHN ↗

I had the same problem for a very long time but it is largely solved now. I started to simply ask chatgpt "hey I read something about x, y month ago but can't find it now". There is a surprisingly high chance chatbot can just give the exact answer back to me, usually with extra interesting reading materials as a plus.

14m agoHN ↗

Is all your browsing history already with chatgpt or something?

This has an MCP server specifically so a workflow like that would work for you. This is just made to gold the data, and I'm a human accessible way should your AI fail you

11m agoHN ↗

No I don't share anything with chatgpt. But I do have a $20 subscription, if it matters. I feel It's just capable enough to find what I want from my usually vague and inaccurate description.

12m agoHN ↗

And now you are even more dependent on OpenAI...

You didn't solve the problem, you are just trading pain points.

10m agoHN ↗

Nothing about this depends on the provider, you could spin up a local Qwen and give it a search tool like SearXNG or something. At this point local models are more than good enough for simple tasks like that. Using ChatGPT is just (usually) faster and simpler

8m agoHN ↗

There should be no real vendor lock in in my opinion. You can ask the same question with pi + qwen (or any harness + good enough model) with internet access and it will work. Chatgpt is just one option came in handy.

13m agoHN ↗

Google Chrome did this in 2008. Full-text search over all visited pages, stored offline. It was very useful and I miss it.

Nobody seems to remember it, even though it was a headline feature. Was removed in 2013, I think due to technical constraints.

Will definitely try this.

7m agoHN ↗

I remember this as well. I hadn't noticed it was gone until just now, but you're right.

12m agoHN ↗

This is really cool. I like the idea of combining it with a offline Wikipedia cache.

7m agoHN ↗

I've been using this since the last time it came up on here. I don't have it index every page I visit, I use the browser plugin to tell it to index specific ones. It is useful for sure, but I think it will really shine once I've been using it long enough for it to build up a bigger index of things that are old enough that I've actually forgotten about them.