Hacker News

Top stories

Live mirror
30 storiesupdated just nowView source snapshot
  1. Ollaya – Ollama for open-source, Jev-style decision models (ollaya.dev)
    47comments
  2. Alan Kay: Shannon gave us a way of dealing with noisy channels [video] (youtube.com)
    15comments
  3. Show HN: Jev Plays Pokémon Red (jev-pokemon.vercel.app)
    29comments
  4. Platform-independent SIMD in Go (go.dev)
    122comments
  5. Advice to a Beginning Graduate Student (2001) (cmu.edu)
    9comments
  6. First Principles Thinking (sunilsadasivan.com)
    73comments
  7. Git-bug: Distributed, offline-first bug tracker embedded in Git (github.com/git-bug)
    89comments
  8. U.S. appeals court upholds designation of Anthropic as supply chain risk (cnbc.com)
    472comments
  9. Show HN: Make math automatic with Mathy (gmays.com)
    3comments
  10. Pentium II at 600Mhz with Voodoo 3 Emulated on 86Box with M6 Mac Mini (nyaa.sh)
    107comments
  11. How video games inspire great UX (2019) (jenson.org)
    5comments
  12. Meta's Muse appears to use an OpenAI model labeled muse-special (mouse.dev)
    27comments
  13. Ink and Switch interactive homepage (inkandswitch.com)
    25comments
  14. Bwbach, My Guardian Goblin (robertmay.photography)
    6comments
  15. Rising sea destroys homes, erases beaches in California (reuters.com)
    4comments
  16. Factorio that you can touch (factorio.com)
    77comments
  17. Bug: Border radius has infected VSCode editor (github.com/microsoft)
    11comments
  18. Amiga Screens: A Primer (datagubbe.se)
    30comments
  19. A History of the Chiming Machines at Gloucester's Cathedral and Churches (2017) [pdf] (bgas.org.uk)
    1comments
  20. Letterboxd Is Up for Sale, and A24, Sony and the New York Times Are Bidding (worldofreel.com)
    10comments
  21. Show HN: Doom or Bloom, map your AI worldview (doom-or-bloom.com)
    29comments
  22. Show HN: Whiteboard (YC W26) – An open-source IDE for thoughtful software design (github.com/devdotfast)
    127comments
  23. What About Rails? (jardo.dev)
    179comments
  24. Typst makes big strides (lwn.net)
    9comments
  25. Why is the liver so weirdly regenerative? (dynomight.substack.com)
    272comments
  26. CVE-2025-13032: Entering and Breaking the Avast Antivirus Sandbox Part 2 (safateam.com)
    27comments
  27. Boards of Casio (ambionix.com)
    31comments
  28. Astronomer watches Starlink satellites sinking to build a 'planetary barometer' (theregister.com)
    9comments
  29. Rails World 2026 Opening Keynote [video] (youtube.com)
    467comments
  30. What happens when you analyze your favorite college football team like the CIA? (cultivatelabs.com)
    9comments

Show HN: Jev Plays Pokémon Red

46 pointsby 6h agojev-pokemon.vercel.app
28 comments
Hey HN! Wanted to share a fun project I've been hacking on. Given Jev can make decisions really fast (but not fast enough to play Doom yet sadly), I wanted to try and push it to play a more complex game than Tetris. So I went with Pokémon.

I've spent endless hours playing this game as a child so building this was a ton of fun.

I open sourced everything in case you want to hack on it yourself here: https://github.com/christianmat/jev-pokemon

The game is being streamed live including the tokens and cost - hopefully we get all the badges and don't get stuck in a cave :)

6h agoHN ↗

That's actually fun to watch. Did you experiment with nicknaming before you turned it off? I'd be a little curious to see how it behaves.

6h agoHN ↗

Jev can't come up with original text, but I did consider giving it a list of hilarious names.

26m agoHN ↗

Sure it can, just ask it for next char or "done" in a loop

6m agoHN ↗

I just took your advice and added it to the list of Jev decisions. Watch it name its next Pokemon!

45m agoHN ↗

with such a fat harness, this is more like watching a walk thru play the game.

15m agoHN ↗

Yeah I would have expected it to only decide which button to press, not something abstract like the choice of "go east to lavender town" for the goal of "in lavender town, climb the pokemon tower"

41m agoHN ↗

Looking at the diagram in the gh repo, it looks like this is entirely jev. Are there any examples of people having a big model like Fable handle high level goals?

28m agoHN ↗

Hm wondering what a first pass optimal setup might be - jev for overworld navigation, escalate to sonnet for easy battles, opus for medium difficulty battles, and fable for gym bosses could probably have jev also manage all the escalation / de-escalation to different models.

13m agoHN ↗

I'm not sure if you're asking about whether using Fable makes playing the game possible or if you're just curious about Jev + LLM interactions.

However, https://x.com/TynanSylvester/status/2096965749369720970 Astra was able to beat RimWorld. So LLMs are definitely able to drive these sorts of games to completion with their current abilities.

40m agoHN ↗

This is kinda chill to have in the background. I wish there were livestreams showing live reasoning of top models which are currently trying to solve cancer or whatever. Imagine the pogs in chat when it does.

36m agoHN ↗

People need to be live streaming their AI more!

30m agoHN ↗

Actually, yes, that would be at least interesting

40m agoHN ↗

watched it stuck at rocket hideout for 10 mins.... let me check 1hr later to see if it can find a way out

26m agoHN ↗

It’s currently stuck at an elevator and deciding to teach Pokemon various TMs and HMs instead of progressing… pretty hilarious!

32m agoHN ↗

but not fast enough to play Doom yet sadly

Did I miss something? I thought one of the demo videos was it doing pretty decent at the first level of Doom?

27m agoHN ↗

In my experience it was too slow to do an FPS with 30 ticks per second reliably. It gets killed too fast.

30m agoHN ↗

Is Frigade going to use Jev to do object detection?

23m agoHN ↗

Nice. When I saw your connection to Frigade, I knew there was a connection haha

28m agoHN ↗

Considering it just made Charizard forget its only fire-type move "Ember" to learn "Counter", I note no signs of intelligence.

23m agoHN ↗

This is so interesting to watch. For a couple minutes I was in awe of how quick and cheap it was. Then I saw just how bad the decision are and how it would get stuck in strange loops of going in and out of the same door to no end.

This seems like a technology heading in the right direction but not quiet there yet. Excited for what they are cooking up but probably won't start building around it yet.

11m agoHN ↗

Like others have mentioned in this post, I think a mix of models like Jev for simple stuff + a smarter reasoning model for more strategic thinking is the optimal solution. This experiment however is purely Jev. Which sometimes can be kinda dumb.

9m agoHN ↗

This entire conversation around Jev seems weird to me. Like... we started from neural nets that could do basic decision making and classifications pretty well, then trained larger and larger language models to get to where we are now. Now suddenly everyone is going crazy because someone trained a smaller model that is adequate at making decisions? We already went through the "look this AI can play pokemon terribly" phase like a decade ago.