Hacker News

New stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Stats: 72% of respondents said they felt curious, happy or excited about AI (marginalrevolution.com)
    —discuss
  2. Agentic ERP (shakegraph.com)
    —discuss
  3. Anthropic to Pay Akamai Technologies $11.6B over Seven Years for Cloud Services (wsj.com)
    —discuss
  4. Accomplishing More with LFM2.5-VL-DSpark (2tinteractive.com)
    1comments
  5. Mercedes-Benz gets first dibs on ProLogium's Gen4 solid-state EV battery cells (electrek.co)
    —discuss
  6. Valen: A multimodal decision model inspired by Jev (github.com/liuziyu77)
    —discuss
  7. The Murky History of Soviet-Born Tetris (mitpress.mit.edu)
    —discuss
  8. GitLab Outage (status.gitlab.com)
    9comments
  9. Show HN: Jev-browse – browser sub-tasks for coding agents at ~1/3 the cost (github.com/danielnc)
    —discuss
  10. It's sinister that Meta's Muse AI mascot is so cute (theverge.com)
    —discuss
  11. MentalHealthBench (openai.com)
    —discuss
  12. CTNicholas Multiplayer-Coding-Agents (github.com/ctnicholas)
    —discuss
  13. Special police to investigate threats to democracy, Swedish election fraud (kvartal.se)
    1comments
  14. Launching FreeBSD/EC2 Desktop AMIs (daemonology.net)
    —discuss
  15. Turbocharging Your Python Workflow (medium.com/therealcomtom)
    —discuss
  16. Award-Winning French Author Accused of Using AI to Write Debut Novel (cbc.ca)
    —discuss
  17. Zuse: Open-Source Cloud Agents (github.com/swarajbachu)
    —discuss
  18. Cal Newport: Here's What to Ask A.I. Leaders (nytimes.com)
    —discuss
  19. One API for Frontier Media Models (comfy.org)
    —discuss
  20. Welcome to the Age of Listening Devices (yahoo.com)
    1comments
  21. Interesting QA Career building book with interview tips (springer.com)
    —discuss
  22. Building an Ultra-High Throughput AI-SQL Engine (fsdatalab.github.io)
    —discuss
  23. Goldman reaped more than $200M in fees from hedge fund Situational Awareness (ft.com)
    —discuss
  24. Bushmen (mapwriting.substack.com)
    1comments
  25. Mini Test Planning: How to add rigor without slowing down QA (qawithahmed.com)
    —discuss
  26. Internet domain subprocess.run redirects to the Python docs for subprocess.run()
    —discuss
  27. Show HN: Sprocket – A bioinformatics workflow engine in Rust, from St. Jude (sprocket.bio)
    —discuss
  28. DraftKings Is Using AI to Supercharge the Harms of Online Behavioral Advertising (eff.org)
    —discuss
  29. A24, Sony, or the New York Times May Soon Swallow Letterboxd (gizmodo.com)
    —discuss
  30. Lessons for Software Developers from Heinlein (2009) (computerworld.com)
    —discuss

Using LLMs to trace alchemical knowledge and decode 17th century letters

48 pointsby 4h agoresobscura.substack.com
9 comments
3h agoHN ↗

This is a strong application of LLMs IMO. They are idea machines. Historical ways of thinking give us different paths to explore the world through.

2h agoHN ↗

I'm guessing it wasn't Claude 5.5, not with the "dangerous" nature of this work.

2h agoHN ↗

Great post, thank you! So, let's resolve ancient Near East chronology and determine an absolute date for the sack of Babylon?

2h agoHN ↗

Great use case of AI. Almost 4 years after the sensational release of GPT3.5, the best use case of AI is still being a powerful search engine that can gather information from all corners of the digital world.

2h agoHN ↗

I've been using AI to help with my genealogical research, and it's been fantastic. I am loving pushing the family history back and catching mistakes that someone who many others share as a common ancestor have made.

2h agoHN ↗

I also have been doing this every round of models releasing.

Thanks for reminding me to try this new round of models.

I wonder if there are some good tools/apis that can help here.

A lot of information is often login gated

1h agoHN ↗

I'm very interested in this topic. I have been using AI for genealogy, but not in ways that have been able to push family history back or catch mistakes (yet).

So how do you use the models more specifically? I have so far used them to write a - in some ways - better genealogy program, with some features I've sorely missed especially with respect to DNA genealogy. I've also tried to use them to help with the tedium of transcribing horrible handwriting, but the results have been so poor and with such a high level of hallucinations that I've not tried that for a while.

14m agoHN ↗

Current models are amazing at one shot decoding hand written vital records. I thought there might be some friction, but if there is, I haven’t found any. I’ve unlocked lots of detail from records I already had just because I didn’t try to translate the handwriting due to the time required.

1h agoHN ↗

FWIW, I have tried my best to make the 10s of thousands of books on https://SourceLibrary.org ergonomic for both agents and people. All feedback welcome.

To date, it is the largest collection of agent-accessible translations on the web. The mcp pulls texts and illustrations — and the API provides access to the embeddings. It’s free.

We are based at the Embassy of the Free Mind in Amsterdam, a UNESCO-recognized library of alchemy, magic and mysticism (among other related topics)

And, it’s worth saying, I’m very much inspired by Res Obscura’s line of curiosity-driven humanist inquiry…

Dive into some historical mysteries, there are so many!