| ▲ | hughw 2 hours ago | |
But it's so easy now to redo it all ground up, and if models improve, do it better next time. I exaggerate only a little. | ||
| ▲ | Jagerbizzle 2 hours ago | parent | next [-] | |
I'm with you on this one, having "vibe coded" some smaller internal tools on GPT 5, and then re-vibed it on Opus 4.6 and 5.5 -- they basically just fixed all of the problems without me doing much of anything other than prompting it to look at the existing code and make it "better". | ||
| ▲ | jimbokun 2 hours ago | parent | prev [-] | |
How much is your budget for tokens? | ||