_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI My Tamagotchi is an RL agent playing Slither.io
ohazi wrote 8 hours 9 min ago:
> (Sent through Gemini to blur my monitor).
Excuse me, what?
Stefan-H wrote 7 hours 49 min ago:
The image is watermarked from gemini, so presumably the author was
trying to allay concerns that the important content was fake.
nkaz123 wrote 7 hours 41 min ago:
Yeah essentially this. The irony of about wanting to obscure
information by submitting it to a model API isn't lost on me, but
it was the easiest way I could think of. Wanted some way of making
the most key content in my picture to be the only thing unblurred
idiotsecant wrote 7 hours 44 min ago:
That doesn't answer the question of why you would use an LLM to
blue your monitor when there are a thousand ways to do it yourself
DonHopkins wrote 6 hours 38 min ago:
Because bluing yourself is messy.
URI [1]: https://www.youtube.com/watch?v=9GYtgFdXCGE
StopDisinfo910 wrote 6 hours 59 min ago:
Why not? You send the picture and ask to blur the monitor in
plain text. It gives you back the picture with a blurred monitor.
That seems like a very easy way to do the job. What's the issue
specifically?
usefulposter wrote 7 hours 39 min ago:
The same reason today's inexperienced programmers depend totally
on NextTailVibeJSFlare. It's all they know.
breakds wrote 8 hours 10 min ago:
The sample efficiency of the RL algorithm, even for simple games, is
not very good. This usually means that we will need a lot of episodes
for the policy to learn to excel. Being able to run policy in an
environment that can parallel and accelerate could be very helpful for
the improvement - for example running a batch of browsers or tabs
simultaneously :)
treyd wrote 8 hours 17 min ago:
I had this idea during the pandemic 5 years ago now, and even did some
of that work to figure out the variables I'd need to extract to make it
work, but I never found the time/motivation to work on it for real.
Really happy to see someone put in the effort.
jeremysalwen wrote 8 hours 37 min ago:
As someone who implemented some RL algorithms and applied them to a
real world game, (including all the ones mentioned in the article), I
would be surprised if the implementation is not buggy. That is one of
the most striking things about RL, the extent to which it is hard to
find bugs, since they generally only degrade the performance instead of
causing a crash or obviously wrong behavior. The fact that he doesn't
mention a massive amount of time spent debugging, and the longish list
of things that were tried that really should have worked but didn't,
suggests to me it's probably still buggy. I suppose it is possible
that LLMs could be particularly good at RL code since it's seen it
repeated so many times... But I would be skeptical without hard
evidence.
nkaz123 wrote 8 hours 11 min ago:
I accepted the bugginess in the browser game as unavoidable, and
probably had too much faith in the LLM implementations, but I did a
bit more troubleshooting than mentioned. The progressive improvement
over episodes (and intuitively that PPO > the others) gave me some
confidence, and I've since used a similar setup on 2048 with more
results showing improvement over episode:
URI [1]: https://wandb.ai/noahpunintended/2048-raspberry-pi?nw=nwuser...
remix2000 wrote 9 hours 9 min ago:
Clicked for Tamagotchi, but I saw none. My day is ruined. :'c
gnyman wrote 7 hours 17 min ago:
It caught my eye also but the article was interesting so I'll forgive
OP :-)
On the topic of tamagotchi, if you happen to have a flipper zero
there is emulator for it :-) my kid enjoyed it for while and it saved
me a few bucks from having to buy one. [1] You can run it on tama-p1
on other platforms also but the flipper was very reminiscent of the
original one.
URI [1]: https://github.com/GMMan/flipperzero-tamagotch-p1
nkaz123 wrote 8 hours 40 min ago:
I'm sorry for the clickbait
giancarlostoro wrote 9 hours 25 min ago:
Corporate firewall is blocking this since its a "newly registered
domain" but I wanted to note that Tamagotchi got me to revisit Digimon
after I learned that Digimon was created as a way for Bandai to sell to
boys. Color me surprised when I learned that Tamagotchi was considered
for girls, but I played with mine like there was no tomorrow, with the
Pokemon hype of the late 90s it came to many of us at the right time.
Surprisingly, and I just looked it up, you can buy the original classic
ones for about $20 straight off Amazon.
nkaz123 wrote 8 hours 34 min ago:
I recently updated my .github.io to route to a domain name I
purchased so that could be why it's getting blocked right now.
This comment alone has more tamagotchi lore than my post as a
disclaimer in case I saved you a read haha.
DIR <- back to front page