Show HN: Jev Plays Pokémon Red (jev-pokemon.vercel.app)

86 points by pancomplex 8 hours ago

42 comments:

by stusmall 2 hours ago

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.

by binlog 2 hours ago

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.

by c7b an hour ago

A pre-trained universal classifier that can replace specifically-trained ones would have been considered just as much science fiction in the 2010's as the capabilities of modern LLMs. I'm not sure Jev is actually there yet, but at least it sounds theoretically doable today.

That being said, one thing having been unrealistic 10 years ago and just about possible today doesn't mean that it's going to change the world the same way another technically related, previously-impossible thing did. The Jev hype gives me a bit of the "you're still early to crypto" vibes of some later altcoins. I really like the idea, I think it's going to open up possibilities for using classifiers where we wouldn't or couldn't have trained one before. I'm crossing my fingers for an open weights version to drop. But it's still just a classifier, people have built similar things before Jev, the one thing that really stands out about it is their ability to generate hype.

by someothherguyy 2 minutes ago

> but at least it sounds theoretically doable today

why

by ford an hour ago

I agree it's overhyped, but the transition to a general purpose classifier (vs a narrow scope classifier) is new and noteworthy.

Ie the famous "Hotdog" clip from Silicon Valley [0]

https://www.youtube.com/watch?v=ACmydtFDTGs

by azan_ an hour ago

Making decisions quickly, cheaply and without having to train your own model.

by joshuat an hour ago

Math.random can make poor decisions quickly and cheaply

by azan_ an hour ago

Benchmark it against jev and you'll have your answer.

by ralusek an hour ago

The exact message I sent my friend this morning:

> the most interesting thing about this jev stuff

> is that people are seemingly like

> completely disinterested in how smart it actually is

> I haven't even heard it mentioned a single time how it actually compares to other LLMs coming up with their own classifications. Just: it's fast and cheap

After watching a few minutes of this it makes me think that maybe we should be a little more interested in how smart it is.

by pancomplex 2 hours ago

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.

by MitPitt 2 hours ago

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.

by tehnoslow 2 hours ago

Actually, yes, that would be at least interesting

by pancomplex 2 hours ago

People need to be live streaming their AI more!

by testaccount28 2 hours ago

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

by laszlokorte 2 hours ago

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"

by pancomplex 32 minutes ago

That was how I first implemented it. Jev sadly never left Pallet Town.

by rickintoplace 8 hours ago

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.

by pancomplex 7 hours ago

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

by JamesSwift 2 hours ago

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

by pancomplex an hour ago

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

by pancomplex 2 hours ago

True!

by IanCal 2 hours ago

Maybe letter by letter spelling?

by djhworld an hour ago

What's not clear to me on the video is whether jev is doing the button presses for controlling the character to move around.

The "Jev calls" counter only seems to increment at junction points like battles, conversation prompts, menus etc.

Is something else moving the character around?

by pancomplex an hour ago

It's connected to the ROM of the actual game, so it can see a lot of things. It has multiple tools available, including being able to move to coordinates.

All in the OSS repo if you wanna play around with it: https://github.com/christianmat/jev-pokemon

by lwarfield 2 hours ago

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?

by pancomplex 2 hours ago

Frontier reasoning models do pretty well in Pokemon: https://github.com/benchflow-ai/pokemon-gym

The interesting thing here imo is the cost and latency. So far we're at 4 badges for less than $0.5

by delichon an hour ago

A Robot is Sprinting Towards You: Do You Want it Running on Claude or Grok?

https://openrouter.ai/blog/insights/royale-last-agent-standi...

by SeanAnderson 2 hours ago

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.

by staindk 2 hours ago

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.

by stusmall 2 hours ago

>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?

by pancomplex 2 hours ago

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

by zaik an hour ago

Seems like it got stuck on a Ghost enemy.

by 361994752 2 hours ago

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

by jumploops 2 hours ago

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

by pancomplex an hour ago

it made it through!

by dmitrygr 2 hours ago

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

by pancomplex 2 hours ago

Rookie mistake clearly..

by theturtletalks 2 hours ago

Is Frigade going to use Jev to do object detection?

by pancomplex 2 hours ago

Working on it :)

by theturtletalks 2 hours ago

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

by avaer an hour ago

I wish jev took in images so we could do this generically for any game, without memhacks. I'm sure that's coming.

You could front this with an image -> text model but that would be much lower quality vs latency, and the whole point of doing it with a decision model is remove the latency.

Games are a really interesting testing ground for robotics; if we can solve game playing (incl 3d) we could embody "system one" intelligence into robots that have something emulating general reflexes without needing to fine tune.

by pancomplex 14 minutes ago

Agreed this would be super cool and I do see that coming in the future. But Jev-level latency just isn't there yet with full images.

Data from: Hacker News, provided by Hacker News (unofficial) API