It looks like the wrong AI for the problem. RL should be more successful.
Came here to read this, it'd actually be a very good project (DIY 2048 AI) to take up to get your hands dirty with Reinforcement Learning.
Show HN: GPT crushes my high score in 2048.io
31–40 of 40 posts
Re: Show HN: GPT crushes my high score in 2048.io
#32Earlier quoted context omitted.
2048 spawns new numbers randomly on the board. A human player uses that information to determine the best move.
Besides that you need to predict where the next number can and should spawn. If you don't figure out the strategy for that you will never get a decent score.
That relies on the board state but not the board history.
Re: Show HN: GPT crushes my high score in 2048.io
#33Earlier quoted context omitted.
There shouldn't need to be any board history, just like you don't need to know the board history to know the next move in checkers.
2048 spawns new numbers randomly on the board. A human player uses that information to determine the best move.
Yes, but that's _state_, not _history_.
Re: Show HN: GPT crushes my high score in 2048.io
#34This is a pretty interesting example, as I think most of you will find that after playing 2048 for a bit, you discover a way to beat the game every time. I'm not sure I could code it up, but the heuristic is basically to keep the big numbers squashed against the same edge (eg the top) the whole game while using left-right-up movements to squash the smaller numbers into each other as opportunities arise. I don't think…
> I've never seen it do anything where I thought it had a parsimonious internal model of the problem. For instance I had it tell me about the quadratic equation, and the explanation was fine. When it came to plugging in numbers, it utterly failed, though the presentation was as if it understood it. If it had just a simple calculator inside it, this wouldn't be a problem.
That's - at the moment, AFAIU - a limitation of the tokenizers used to interface with LLMs. Basically, the model "calculates" bullshit because the input layer doesn't get correct inputs from the tokenizer.
Re: Show HN: GPT crushes my high score in 2048.io
#35My highest score on 2048 was in 2015 when I scored over 120,000. I was close but failed to achieve the 16384 block. If an AI were trained to play that game I would expect similar performance, because there are very few strategies to this game but those strategies will comprise multiple moves to solve for a given problem in the moment.
I also modified the original game code to allow a board of different sizes. The modifications are just a minor fix to the CSS, an input field for board size, an the corresponding JS for that input field.
Re: Show HN: GPT crushes my high score in 2048.io
#36GPT4 just told me that a billion golf balls take up 40 billion cc, and since packing efficiency of spheres is as high as 74%, they take up 26 billion cc. No, you have to divide by 0.74, not multiply. In shit that GPT4 is not trained on (like code code code and more code), it can get really goofy. Earlier in the same chat about golf balls, it claimed that if brain cells were the size of golf balls (an imaginary thread…
Yet according to many HNers we're scarce months from AGI that can replace programmers or synthesise 6-season TV series. :)
Given that a lot of what programmers do is write CRUD-style apps and a lot of TV shows and movies - particularly the big IPs - follow one and the same formula... it's not like that argument has some merit.
AI is rapidly approaching a quality level near to "good enough with a bit of human cleanup afterwards".
Re: Show HN: GPT crushes my high score in 2048.io
#37Earlier quoted context omitted.
Yet according to many HNers we're scarce months from AGI that can replace programmers or synthesise 6-season TV series. :)
Given that a lot of what programmers do is write CRUD-style apps and a lot of TV shows and movies - particularly the big IPs - follow one and the same formula... it's not like that argument has some merit. AI is rapidly approaching a quality level near to "good enough with a bit of human cleanup afterwards".
[dead]
Re: Show HN: GPT crushes my high score in 2048.io
#38Earlier quoted context omitted.
Yet according to many HNers we're scarce months from AGI that can replace programmers or synthesise 6-season TV series. :)
Given that a lot of what programmers do is write CRUD-style apps and a lot of TV shows and movies - particularly the big IPs - follow one and the same formula... it's not like that argument has some merit. AI is rapidly approaching a quality level near to "good enough with a bit of human cleanup afterwards".
And even then with CRUD apps isn't main work to define what you CRUD. And what is the involved rules. The writing is mostly busy work that should actually be standardized already.
For average episodic TV show, yeah. Just pull things from hat and fill the holes, later that could be done by pretty cheap writers already.
Re: Show HN: GPT crushes my high score in 2048.io
#39GPT4 just told me that a billion golf balls take up 40 billion cc, and since packing efficiency of spheres is as high as 74%, they take up 26 billion cc. No, you have to divide by 0.74, not multiply. In shit that GPT4 is not trained on (like code code code and more code), it can get really goofy. Earlier in the same chat about golf balls, it claimed that if brain cells were the size of golf balls (an imaginary thread…
Pretty smart for a 3-year-old if you ask me.
Re: Show HN: GPT crushes my high score in 2048.io
#40This is a pretty interesting example, as I think most of you will find that after playing 2048 for a bit, you discover a way to beat the game every time. I'm not sure I could code it up, but the heuristic is basically to keep the big numbers squashed against the same edge (eg the top) the whole game while using left-right-up movements to squash the smaller numbers into each other as opportunities arise. I don't think…
I’m not sure if you know yet, but one of the first ChatGPT plugins was WolframAlpha. That adds a rather advanced calculator to it’s toolset.