ravroid

Also in Valencia and the beach is a great idea.

Didn't know about Aider - going to give that a try, thanks!

One strategy I've been experimenting with is maintaining a 'spec' document, outlining all features and relevant technical notes about a project. I include the spec with all relevant source files in my prompt before asking the LLM to implement a new change or feature. This way it doesn't have to do as much guessing as to what my code is doing, and I can avoid relying on long-running conversations to maintain context. Instead, for each big change I include an up-to-date spec and all of the relevant source files. I update the spec to reflect the current state of the project as changes are made to give the LLM context about my project (this also doubles as documentation).

I use an NPM script to automate concatenating the spec + source files + prompt, which I then copy/paste to o1. So far this has been working somewhat reliably for the early stages of a project but has diminishing returns.

I imagine this would be cost prohibitive at scale since it would require two models to run for every user message?

Important to note that it's not what all of us Americans want, it's just what a little over half of the voting population voted for.

In my experience so far, GPT-4o seems to sit somewhere between the capability of GPT-3.5 and GPT-4.

I'm working on an app that relies more on GPT-4's reasoning abilities than inference speed. For my use case, GPT-4o seems to do worse than GPT-4 Turbo on reasoning tasks. For me this seems like a step-up from GPT-3.5 but not from GPT-4 Turbo.

At half the cost and significantly faster inference speed, I'm sure this is a good tradeoff for other use cases though.