pancomplex

Thank you! It finished the full game!

Are you ok bro?

The next version I make should take advice like this from the chat

It has continued to surprise me throughout all of this so hopefully it will again

It has the option to go back and level up its pokemons + switch it up. Hopefully it gets the same idea as you soon!

I wrote down a series of 33 high level goals + some sub goals for completing the game

Fair point, but I’d challenge anyone to build an ai or hard coded engine that, even following a walkthrough, completes the entire game for under $2 in tokens

Thank you. What I realized is that Jev is incredibly powerful for the decision making part of it when presented with a scenario that gives it a little context. It looks like we’re gonna be able to beat this game for under $2 of tokens. This is what blows my mind

The more the merrier!

I challenge you to fork the repo and solve it faster using less tokens/cost than Jev :)

This runs entirely on Jev as the only AI with a typescript harness that feeds it selective context.

Thank you! And interesting data point on Fable burning out on tokens so early.

Nothing fake here and fully open source if you wanna take a peek. It does make a bunch of mistakes, often. But it eventually recovers!

https://github.com/christianmat/jev-pokemon

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.

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

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

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

it made it through!

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.

Rookie mistake clearly..

True!

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

Working on it :)

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

People need to be live streaming their AI more!

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

Thank you!

Very much agree with the sentiment here - I actually even wrote a blog post about this specific issue lately. There's an entirely separate issue of AI slop ruining well-defined clean applications: https://frigade.com/blog/easier-to-build-not-easier-to-use

Yes for sure. We actually use the map we build of the UI + the questions people ask to automatically identify product gap patterns. These are the presented in a dashboard where you can use these insights to improve the product itself.

I'm considering adding a feature to include auto punctuation and capitalization. Would that solve it for you?