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

Agentic Coding Recommendations

lucumr.pocoo.org

Post reply on HN
Print view View original

171–180 of 210 posts

Re: Agentic Coding Recommendations

#171

Post by Karrot_Kream »

BeetleB wrote: post #151
tonnydourado wrote: post #65

Gotta say, 100/200 bucks monthly feels prohibitively expensive for even trying out something, particularly something as unproven as code-writing AI, even more particularly when other personal experiences with AI have been at the very least underwhelming, and extra particularly when the whole endeavor is so wrapped up in ethical concerns.

Try Aider with API usage. Learn how to control context size (/clear, /add, /drop). Limit context to 25K. Use whatever model you want (Sonnet 4 or Gemini 2.5 Pro). For simple scripts, it often costs me under $1 to build. I'm working on a bigger tool these days, and I've done lots of prompts, a decent amount of code, over 100 tests, and my running total is right now under $6. I'd suggest learn the basics of using AI to…

Yeah I've been using Aider mostly and just started using Codex, very similar to Claude Code, yesterday. Aider is more manual and requires more guiding but it's also an order of magnitude cheaper.

The monkey brain part of me that really doesn't trust an LLM and trusts my decades of hard-won programming experience also prefers using Aider because the usage flow generally goes:

1. Iterate with Aider on a plan

2. Tell Aider to write code

3. Review the code

4. Continue hacking myself until I want to delegate something to an LLM again.

5. Head back to Step 1.

Codex automates this flow significantly but it's also a lot more expensive. Just the little bits of guiding I offer an LLM through Aider can make the whole process a lot cheaper.

It's unclear to me whether the full agentic Claude Code/Codex style approach will win or whether Aider's more carefully guided approach will win in the marketplace of ideas, but as a pretty experienced engineer Aider seems to be the sweet spot between cost, impact, and authorial input.

Re: Agentic Coding Recommendations

#172

Post by Karrot_Kream »

diggan wrote: post #122
CuriouslyC wrote: post #10

Earlier quoted context omitted.

Aider is almost there, in fact it's intentionally "not" there. You can set it up to do things like run test/static analysis automatically and fix errors, and work with it to get a to-do list set up so the entire project is spec'd out, then just keep prompting it with "continue...". It has a hard coded reflection limit of 3 iterations right now, but that can also be hacked to whatever you want. The only thing missing…

> The only thing missing for full agentic behavior is built in self prompting behavior. Correct me if I'm wrong, but Aider still doesn't do proper tool calling? Last time I tried it, they did it the "old school" way of parsing out unix shell commands from the output text and ran it once the response finished streaming, instead of the sort of tool call/response stuff we have today.

There's an open PR for MCP integration (actually 2 PRs but one has more community consensus around it) with a Priority label on it but it hasn't been merged yet. Hopefully soon.

Re: Agentic Coding Recommendations

#173

Post by BeetleB »

Karrot_Kream wrote: post #171
BeetleB wrote: post #151

Earlier quoted context omitted.

Try Aider with API usage. Learn how to control context size (/clear, /add, /drop). Limit context to 25K. Use whatever model you want (Sonnet 4 or Gemini 2.5 Pro). For simple scripts, it often costs me under $1 to build. I'm working on a bigger tool these days, and I've done lots of prompts, a decent amount of code, over 100 tests, and my running total is right now under $6. I'd suggest learn the basics of using AI to…

Yeah I've been using Aider mostly and just started using Codex, very similar to Claude Code, yesterday. Aider is more manual and requires more guiding but it's also an order of magnitude cheaper. The monkey brain part of me that really doesn't trust an LLM and trusts my decades of hard-won programming experience also prefers using Aider because the usage flow generally goes: 1. Iterate with Aider on a plan 2. Tell Ai…

Yes, my concerns as well about the more powerful tools (which I admit I haven't tried).

Even with Aider, I feel it goes too fast and I sometimes actively slow it down (by giving it only very incremental changes rather than get it to do a larger chunk). I think I'd be totally lost with a more powerful agentic tool.

Re: Agentic Coding Recommendations

#174

Post by Leynos »

skydhash wrote: post #155
Leynos wrote: post #150

Earlier quoted context omitted.

Do you give the agent a style guide? Do you perform (or have another agent perform) code reviews on the agent's code? Do you discuss architecture and approach with the agent beforehand and compile that discussion into a design and development plan? If you don't do these things, then you're just setting yourself up for failure.

That’s just the hallmark of good software engineering or do you think everyone else was cowboy coding things with Vim before?

Seemingly so going by the sibling comment to yours.

Re: Agentic Coding Recommendations

#175

Post by Leynos »

bluefirebrand wrote: post #154
Leynos wrote: post #150

Earlier quoted context omitted.

Do you give the agent a style guide? Do you perform (or have another agent perform) code reviews on the agent's code? Do you discuss architecture and approach with the agent beforehand and compile that discussion into a design and development plan? If you don't do these things, then you're just setting yourself up for failure.

Ah yes the tried and true "you're holding it wrong" By the time I did all the stuff you're suggesting, I could just build the damn thing myself

Would you skip these guardrails when working with a "Junior to Intermediate" developer?

Re: Agentic Coding Recommendations

#176

Post by diggan »

BeetleB wrote: post #147
diggan wrote: post #117

Earlier quoted context omitted.

> AI discourse would be more effective if we could all see the actual work one another is doing with it Yes, this is a frequent problem both here and everywhere else. The discussions need to include things like exact model version, inference parameters, what system prompt you used, what user prompt, what code you gave it, what exactly it replied and so much more details, as currently almost every comment is "Well, I…

> The discussions need to include things like exact model version, inference parameters, what system prompt you used, what user prompt, what code you gave it, what exactly it replied and so much more details, as currently almost every comment is "Well, I used Sonnet last week and it worked great" without any details...Not to mention discussions around local models missing basic stuff like what quantization (if any) a…

> the amount of details you're asking for is

I'm not asking for anything, nor providing anything as "a solution", just stating a problem. The second paragraph in my comment is quite literally about that.

Re: Agentic Coding Recommendations

#177

Post by 8note »

andnand wrote: post #126
darkxanthos wrote: post #48

I stumbled into Agentic Coding in VS Code Nightlys with co-pilot using Claude Sonnet 4 and I've been silly productive. Even when half my day is meetings, you wouldn't be able to tell from my git history. My thinking now is removed from the gory details and is a step or two up. How can I validate the changes are working? Can I understand this code? How should it be structured so I can better understand it? Is there mo…

Whats your workflow? Ive been playing with Claude Code for personal use. Usually new projects for experimentation. We have Copilot licenses through work so I've been playing around with VS Code agent mode for the last week. Usually using 3.5, 3.7 Sonnet or 04-mini. This is in a large Go project. Its been abysmal at everything other than tests. I've been trying to figure out if I'm just using the tooling wrong but I f…

make sure it writes a requirements and design doc for the change its gonna make, and review those. and, ask it to ask you questions about where there's ambiguity, and to record those responses.

when it has a work plan, track the workplan as a checklist that it fills out as it works.

you can also atart your conversations by asking it to summarize the code base

Re: Agentic Coding Recommendations

#178

Post by bluefirebrand »

Leynos wrote: post #175
bluefirebrand wrote: post #154

Earlier quoted context omitted.

Ah yes the tried and true "you're holding it wrong" By the time I did all the stuff you're suggesting, I could just build the damn thing myself

Would you skip these guardrails when working with a "Junior to Intermediate" developer?

No, but the goal of mentoring a Junior or Intermediate developer is that they eventually learn this stuff on their own. The value of helping another human grow is worth the tradeoff

AI is a tool, not a human. I'm not about to invest in it the way I would a Junior developer. If the tool doesn't do the job, it's not a good tool. If a tool requires the same level of investment that a human does it's also not a good tool

Re: Agentic Coding Recommendations

#179

Post by spacechild1 »

vultour wrote: post #105
spacechild1 wrote: post #91

Earlier quoted context omitted.

I'm having a very good experience with ChatGPT at the moment. I'm mostly using it for little tasks where I don't remember the exact library functions. Examples: "C++ question: how do I get the unqualified local system time and turn into an ISO time string?" "Python question: how do I serialize a C struct over a TCP socket with asyncio?" "JS question: how do I dynamically show/hide an HTML element?" (I obviously don't…

The problem with this approach is that you might lose important context which is present in the documentation but doesn’t surface through the LLM. As an example, I just asked GPT-4o how to access Nth character in a string in Go. Predictably, it answered str[n]. This is a wildly dangerous suggestion because it works correctly for ASCII but not for other UTF8 characters. Sure, if you know about this and prompt it furth…

> The problem with this approach is that you might lose important context which is present in the documentation but doesn’t surface through the LLM.

Oh, I'm definitely aware of that! I mostly do this with things I have already done, but can't remember all the details. If the LLM shows me something new, I check the official documentation. I'm not into vibe coding :) I still want to understand every line of code I write.

Re: Agentic Coding Recommendations

#180

Post by SparkyMcUnicorn »

andnand wrote: post #165
SparkyMcUnicorn wrote: post #156

Earlier quoted context omitted.

Switch to using Sonnet 4 (it's available in VS Code Insiders for me at least). I'm not 100% sure but a Github org admin and/or you might need to enable this model in the Github web interface. Write good base instructions for your agent[0][1] and keep them up to date. Have your agent help you write and critique it. Start tasks by planning with your agent (e.g. "do not write any code."), and have your agent propose 2-3…

This is exactly what I was looking for. Thanks! Im trying to give these tools a fair shot before I judge them. Ive had success with detailed prompts and letting the agent jump straight in when working on small/new projects. Ill give more planning prompts a shot. Do you change models between planning and implementation? I've seen that recommended but it's been hard to judge if that's made a difference.

Glad I could help!

Sometimes I do planning in stronger models like Gemini 2.5 Pro (started giving o3 a shot at this the past couple days) with all the relevant files in context, but often times I default to Sonnet 4 for everything.

A common pattern is to have the agent write down plans into markdown files (which you can also iterate on) when you get beyond a certain task size. This helps with more complex tasks. For large plans, individual implementation-phase-specific markdown files.

Maybe these projects can provide some assistance and/or inspiration:

- https://www.task-master.dev/

- https://github.com/Helmi/claude-simone

Post reply on HN