51–60 of 225 posts
Earlier quoted context omitted.
GPT-4 32k can fit a few thousand lines of code into a single prompt and output diff's, patches, and/or the fully modified code. For best results, pasting any relevant documentation into the prompt can help.
Is there word of ane outside big co's getting access to 32k ? I got 8k access pretty quickly but no word whatsoever about 32k (and my current prompts + context already reach 8-9k tokens)
Earlier quoted context omitted.
Is there word of ane outside big co's getting access to 32k ? I got 8k access pretty quickly but no word whatsoever about 32k (and my current prompts + context already reach 8-9k tokens)
I'm paying for chatgpt. How can I tell what input token size I get?
Earlier quoted context omitted.
Is there word of ane outside big co's getting access to 32k ? I got 8k access pretty quickly but no word whatsoever about 32k (and my current prompts + context already reach 8-9k tokens)
I'm paying for chatgpt. How can I tell what input token size I get?
I would explain my problem to 3.5 and ask it to suggest comprehensive prompts to use with 4 to maximize my limited quota. It worked very well.
In the long years to come the most advance AIs may become so far removed from us that the best intermediaries will be their less advanced brethren.
It's pretty clear that, given terminal access and an appropriate outer loop, GPT models can iteratively create new GPT models (either by writing and executing Pyhton code, or later versions trained on LLM weights may even be able to output new weights directly). If the inner workings of the loop are sufficiently obfuscated (in the code-based version), it wouldn't necessarily be clear to us what had changed, and the model weights/architecture on their own are not interpretable. That's very close to a singularity definition (machines that self-improve faster than what our understanding can keep up with), the only open question is whether the new versions would actually be improvements. But that sounds solvable too (except that it wouldn't be easy for us to tell for sure).
Earlier quoted context omitted.
Copilot without -x does this relatively well. But it's a hands-on process. I can't just give it some source files and say "go". But it can easily make you 10x. I often spend more time tab-completing than writing.
I'm still trying to figure out how to do this. Copilot is extremely helpful. But more often than not, it suggests completions which would steer the project in another direction. It is extremely good once the code has been organised and an overall structure exists. But until then it can be a distraction.
I’m hopeful for -x version though.
> Finally, it was also tiring. Imagine being reduced to giving only instructions and doing code review. Reading and understanding code is tiring!
Earlier quoted context omitted.
What value does driver deliver if entire process is done by a car?
Not much, hence I dont need a dedicated driver to drive my car.
What value does a developer deliver when their entire process is done by an LLM? Is there no desire for a creative process?
They’re not going to be coding tomorrow.