Comment by Gigachad
5 hours ago
I've observed the same thing where the new models want to run obscene bash commands or python scripts which are completely unreadable and utilise every option flag that exists.
It's impossible to review. These commands are less readable than regex.
I noticed that too so I appended to Claude Code’s system prompt a reminder to use the standard read/write tools, but since Claude Code switched to default auto-mode, I’ve seen it imply that the auto-mode tooling encourages the use of bash-only commands (sed, python, etc) which has a whole slew of negative side affects.
Yes.. this happened recently. I basically always use auto mode, and when I asked it why it kept editing code with python, it explained that this is part of its prompt when auto mode is turned on.
I can only assume that's because their safety verification model is better at such snippets or something, but it means that the whole write tool they have which actually shows you the changes as they happen is just unused and it makes it more annoying to follow along.
If these tools are as clever as they seem then why not just tell them to rewrite the code in a more review friendly style?
I only dabble in the use of LLMs to generate code for hobby programming (I'm retired from software development) so I don't use any specialised tools.
I almost always have to tell ChatGPT (via Duck AI usually) to rewrite several times even when it has produced a workable script just because it has often used some unnecessarily roundabout way of achieving something. Usually with extra prompting I can get something that is both more efficient and more readable.
I get around this by asking it to stage changes in reviewable groups.
I make commits based on these -- or ask the LLM to make changes to the "staged changes" only.