Hacker News Reader

Comment by jeswin | Hacker News Reader

> novel and complex things

a) What's an example?

b) Is 90% (or more) of programming mundane, and not really novel?

If you'd like a creative waste of time, make it implement any novel algorithm that mixes the idea of X with Y. It will fail miserably, double down on the failure and hard troll you, run out of context and leave you questioning why you even pay for this thing. And it is not something that can be fixed with more specific training.

Can you give an example? Have you tried it recently with the higher-end models?

My favorite example is implementing NEAT with keras dense layers instead of graphs. Last time I tried with claude 3.7, it wrote code to mutate the output layer (??). I tried to prevent that a few times and gave up.

This NEAT? https://web.archive.org/web/20231205130538/http://www.cs.ucf...

Is the idea to use a keras dense layer to represent a weighted graph by identifying the input nodes with the corresponding outputs?

The idea is to evolve the multi layer dnn using ga

Is there a precise description of what you're trying to do? Maybe the task you gave Claude?

Are you collecting works for anthropic lol

I have asked chatgpt reasoning model to solve chess endgames where white had king and a queen vs king and a rook on a 7x8 chessboards. So to compute value for all positions and find the position which is the longest win for white.

Not creative, not novel and not difficult algorithmic task. But it requires some reasoning, planning and precision.

It failed miserably.

I think you need to be more specific about which "chatgpt reasoning model" you used. Even the free version of chatgpt has reasoning/thinking now but there are also o1-mini, o1, o1-pro, o3-mini, o3, and o4-mini and they all have very different capabilities.

o4-mini-high did make an error I had to point out, on the first attempt: https://chatgpt.com/share/680eeea2-264c-800e-8497-3903ea6309...

Reply on news.ycombinator.com