These are zip files, containing mostly json files, some markdown and a csv file. The tasks gets assigned a UUID. Is this a format that makes sense?
I'm using LlamaIndex so it's not tied to a particular LLM provider. I prefer using OpenRouter with the new Gemini 2.0 Flash. And I also like Ollama with Llama3.1 where I can inspect the logs as the code is running.
I'm using Luigi for a DAG representation of the data being exchanged between the many agents.
Instead of e, I have tried other constants such as pi, but it doesn't look as good.
I guess there is another constant that makes the distribution look even nicer.
I don't think this is anything special about primes or e - if you replace prime(n+1) with just (n+1) itself you get the same sort of patterns. But it is something to do with approximations of irrationals by rationals - you might want to look into continued fractions. Try replacing e with a rational number a/b (say 8/3 or 11/4); then you get b horizontal-ish lines, corresponding to the different remainders of n when divided by b. So the pattern you get with pi isn't "as good" because pi is famously close to 22/7.
There are 100 tasks that is hidden from the public, that is only exposed, when running on an offline computer. So the solver has no prior knowledge about what these tasks are about.
Humans can try the 800 tasks here. There is no time limit. I recommend not starting with the `expert` tasks, but instead go with the `entry` level puzzles.
https://neoneye.github.io/arc/?dataset=ARC
If a model jumps to 100%, that may be a clever program or maybe the program has been trained on the 100 hidden tasks. Fchollet has 100 more hidden tasks, for verifying this.
Not sure what you mean. There's a viable answer that's marked incorrect. The examples should show the pattern well enough to eliminate possible wrong answers, correct?
