That’s a great outcome for 2 hours.
If you’re willing to share, what was your rough workflow/prompt sequence (project overview → reproduce → propose patch → add tests → iterate)?
There's a ton of Claude spam on HN ramping up at the end of 2025 and into the new year. There's a huge push by them to be seen as the LLM for techies. Won't be surprised to see a future marketing campaign about "chatgpt is for homework, claude is for science"
That’s a great outcome for 2 hours. If you’re willing to share, what was your rough workflow/prompt sequence (project overview → reproduce → propose patch → add tests → iterate)?
Does anybody care? No? Nobody cares what the paid shill has to say, ok moving on...
There's a ton of Claude spam on HN ramping up at the end of 2025 and into the new year. There's a huge push by them to be seen as the LLM for techies. Won't be surprised to see a future marketing campaign about "chatgpt is for homework, claude is for science"
Paid shill? OP's name is in public. He was transparent of what he did.
https://github.com/Lallassu
Who are you?