Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Using AI to write better code more slowly

nolanlawson.com

Post reply on HN
Print view View original

51–60 of 511 posts

Re: Using AI to write better code more slowly

#51

Post by sunsetSamurai »

bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

maybe it's dumb question, but how do you feed the results of one agent to another? do you copy and paste manually? or how do you do it programmatically?

Re: Using AI to write better code more slowly

#52

Post by foobarbecue »

vessenes wrote: post #24

One thing that's been interesting to me over the last few years is charting the edge of my coding laziness. As a coder, I'm lazy about boilerplate code -- I hate writing it, I hate maintaining it, etc. And so I design and architect (or used to) around that preference. Sometimes that's smart, sometimes that's not. But it was my preference, and I avoided something that was hard for me to do. When LLMs started being som…

The thing about boilerplate is that a good library or framework makes it optional, and / or automatically written.

I'd much rather django-admin startproject, npm init, or meteor create and get deterministic output than prompt an LLM and get who knows what.

In a mature web ecosystem, boilerplate is minimal. I worry now that we've given this task to LLMs, less development effort will go into startproject-esqe CLIs and good opinionated defaults.

Re: Using AI to write better code more slowly

#53

Post by ianm218 »

ai_fry_ur_brain wrote: post #45

Just dont use it lol, it does nothing you cant do by yourself. You're nerfing parts of your brain by relying on it.

There is things you really can't do by yourself. I've been working on porting some large codebases to Rust lately to experiment with fixing memory safety bugs. There is just no way you can write 100k LOC in a week of production code with tons of tests etc. Even "10X" engineers just can't type that fast.

Re: Using AI to write better code more slowly

#54

Post by adrianN »

sunsetSamurai wrote: post #51
bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

maybe it's dumb question, but how do you feed the results of one agent to another? do you copy and paste manually? or how do you do it programmatically?

Having the agents write their plans into text files and iterating on those works reasonably well.

Re: Using AI to write better code more slowly

#55

Post by th0ma5 »

zik wrote: post #38
justinlivi wrote: post #11

I find myself spending on average more time in LLM review/resolution loops than it would take for me to write the code by hand. Partially because once I'm in the flow I write very very quickly and the code pours out sometimes faster than I can write. But also because the LLM code on the first few tries is generally really really bad. What I find interesting though is that spending the time to personally review and di…

If your AI is writing bad code then you need to change your AI. No current high-end AI should be producing bad code.

[dead]

Re: Using AI to write better code more slowly

#56

Post by kevinsync »

sunsetSamurai wrote: post #51
bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

maybe it's dumb question, but how do you feed the results of one agent to another? do you copy and paste manually? or how do you do it programmatically?

When I pair Claude and Codex, I use claude-co-commands [0] to drive from Claude and talk to Codex via MCP. Lately I've found Codex has been far more consistent for my specific projects, so I've just been almost entirely inside Codex. YMMV

[0] https://github.com/SnakeO/claude-co-commands

Re: Using AI to write better code more slowly

#57

Post by foo12bar »

slopinthebag wrote: post #10

I use cheaper models (Deepseek is king, but GLM and Kimi as well) and do the planning myself. I often start a task myself, write some code to get the LLM on the right track, and then have it complete parts of the implementation that are kind of boring or repetitive. LLM's are just next token predictors, I don't mean that in a demeaning way, but I've found if I can get the LLM started on the right track with my own co…

What app do you use with deepseek? I've been used claude code but pointing it at the deepseek api and it works ok, but I'm wondering if there are better options. (https://api-docs.deepseek.com/quick_start/agent_integrations...)

Re: Using AI to write better code more slowly

#58

Post by ctrl-alt-zen »

ai_fry_ur_brain wrote: post #45

Just dont use it lol, it does nothing you cant do by yourself. You're nerfing parts of your brain by relying on it.

Yeah, agreed. “Cognitive surrender” is one way of describing that loss of personal faculty. I don’t think AI proponents are acknowledging second order effects of letting your mind interact less and less while requesting more and more complexity built for you without adequate verification.

Re: Using AI to write better code more slowly

#59

Post by aomix »

bottlepalm wrote: post #4

I've hit this point with AI where it's not a simple process, but a long drawn out back and forth. I'll use AI to design the implementation of a medium sized, cross cutting feature. Review all the details, maybe iterate on just that. Then implement with Claude 4.7 Max - which runs slower, but does a better job. Then review the implementation, then have Codex GPT 5.5 xhigh fast review it - which almost always finds cor…

Talking the problem to death with the AI before implementation is a nice zone for me. I feel productive, get good results out of the AI, and still largely understand the code. That’s the part of the AI revolution that I feel has made me a better engineer because I argue about design and architecture all day with a robot.

Re: Using AI to write better code more slowly

#60

Post by scosman »

deadbabe wrote: post #41
scosman wrote: post #19

Earlier quoted context omitted.

yes exactly. Too many people ask AI to one-shot complex tasks, and wonder it behaves like a junior asked to rush something. I have my own skill: 5 rounds of research/planning/test-planning. Interactive with me in loop for all important decisions. Starts with high level shape, then details. Planning can take 2-3 days of my time, then the implementation agent can take many hours (Opus 4.7). It splits the implementation…

Does the 5x faster including shipping? Or just the work part? IMO if you are not shipping out faster then the faster work gains are meaningless. If you are shipping faster, you’re probably picking up more work and shipping everything too fast leading to burnout.

yup.
Post reply on HN