Ask HN: Anyone struggling to get value out of coding LLMs?

Re:Ask HN: Anyone struggling to get value out of coding LLMs? by max_on_hn on Monday May 26, 2025 @12:09PM (#44098743)

(disclaimer: I have a vested interest in the space as the purveyor of an AI software development agent)

The result you described is coming soon. CheepCode[0] agents already produce working code in a satisfying percentage of cases, and I am at most 3 months away from it producing end-to-end apps and complex changes that are at least human-quality. It would take way less if I got funded to work on it full time.

Given that I'm this close as a solo founder with no employees, you can imagine what's cooking inside large companies.

[0] My product, cloud-based headless coding agents that connect directly to Linear, accept tickets, and submit GitHub PRs

[ Parent | on HN ]

Re:Ask HN: Anyone struggling to get value out of coding LLMs? by johnecheck on Monday May 26, 2025 @01:38PM (#44099648)

"At most 3 months away"

This is a strong claim. I'm not aware of any AI model or system that can consistently and correctly make complex changes in existing codebases. What makes you so confident that you can achieve this, alone, in the next 3 months?

[ Parent | on HN ]

Re:Ask HN: Anyone struggling to get value out of coding LLMs? by t917910 on Monday May 26, 2025 @10:04PM (#44103308)

The circumference of a circle is easily calculated as piradius2, so calculating the same length of an ellipse would not be much more difficult. Hehe.

[ Parent | on HN ]