This is so interesting to watch. For a couple minutes I was in awe of how quick 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.
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?
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.
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.
This is so interesting to watch. For a couple minutes I was in awe of how quick 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 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?
In my experience it was too slow to do an FPS with 30 ticks per second reliably. It gets killed too fast.
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?
There 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
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.
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.
Actually, yes, that would be at least interesting
People need to be live streaming their AI more!
Is Frigade going to use Jev to do object detection?
Working on it :)
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.
Jev can't come up with original text, but I did consider giving it a list of hilarious names.
Sure it can, just ask it for next char or "done" in a loop
True!
Maybe letter by letter spelling?
Considering it just made Charizard forget its only fire-type move "Ember" to learn "Counter", I note no signs of intelligence.
with such a fat harness, this is more like watching a walk thru play the game.
watched it stuck at rocket hideout for 10 mins.... let me check 1hr later to see if it can find a way out
It’s currently stuck at an elevator and deciding to teach Pokemon various TMs and HMs instead of progressing… pretty hilarious!