←back to thread

How to build a coding agent

(ghuntley.com)
469 points ghuntley | 2 comments | 24 Aug 25 03:21 UTC | HN request time: 0.004s | source
Show context
faangguyindia ◴[24 Aug 25 04:33 UTC] No.45001426[source]▶
Anyone can build a coding agent which works on a) fresh code base b) when you've unlimited token budget

now build it for old codebase, let's see how precisely it edits or removes features without breaking the whole codebase

lets see how many tokens it consumes per bug fix or feature addition.

replies(4): >>45001529 #>>45001567 #>>45001784 #>>45001830 #
simonw ◴[24 Aug 25 04:59 UTC] No.45001529[source]▶
This comment belongs in a discussion about using LLMs to help write code for large existing systems - it's a bit out of place in a discussion about a tutorial on building coding agents to help people understand how the basic tools-in-a-loop pattern works.
replies(1): >>45001675 #
1. faangguyindia ◴[24 Aug 25 05:35 UTC] No.45001675[source]▶
anyone who used those coding agent can already see how it works, you can usually see agent fetching files, running commands, listing files and directories.

i just wrote this comment so people aren't under false belief that it's pretty much all coding agents do, making all this fault tolerant with good ux is lot of work.

replies(1): >>45003705 #
2. ghuntley ◴[24 Aug 25 12:20 UTC] No.45003705[source]▶
> making all this fault tolerant with good ux is lot of work.

Yes, it is. Not only in the department of good design in UX, but these LLMs keep evolving. They are software with different versions, and these different versions are continually deployed, which changes the behavior of the underlying model. So the harness needs to be continually updated to remain competitive.