Technology

A thing I found quite amusing about the AI agents I've toyed with is that they have a step where they do a code review of their changelist, usually switching to a different "persona" when they write it so that they're not seeing it as "their own" code. It's funny reading at the critiques and compliments it gives the "other agent" it's checking the changes for.

I haven't seen this feature yet, but it might be a good future enhancement to ensure that the harness literally uses a different model for the code review from the one that wrote the code in the first place. If Claude wrote the code have GPT do the review, and vice versa, for example. Wouldn't be surprised if the feature exists and I just haven't spotted it yet though, things change fast.

There's also the aspect of giving the LLM another prompt, and another, and another - have it build up a local documentation set based on its internet research, continue to research and refine the local documentation set keeping the things you trust, filtering out the sketchy stuff...

Ultimately, the LLM is a tool you are using. If you use it like a 4th grader copying a paragraph out of the Encyclopedia - you're probably not going to get great results; especially because today's reference materials aren't highly edited / vetted material like encyclopedias were, today's reference materials are internet forums full of self-confident idiots blathering on about whatever they think they know something about (like me, here...) So, back to the tool thing: if you use it well, you can make nice things. If you use it lazily, don't be surprised when your boss decides he doesn't need you at your salary to push that button.

using the right tools and giving them the right instructions.

The right tools is definitely key. Back an eternity ago, like October 2025, there was only Claude IMO if you wanted anything bigger than about a page of code. The others have come a long way - better than Claude was then, and I still feel like Claude is out in front, though by a less dramatic margin now.

As for "the right instructions" - I'd say it's more of "use the right process" which basically involves applying all those best practices that have developed over the past decades for human development, but we old farts from back before their time "don't need all that, it's a waste of time" because, basically, we internally practice most of the discipline without doing the documentation. With the AI tools: document your requirements, your architecture, tool choice selection process, designs, development plan, comment the code with traceability to why the code is being written, unit and integration tests, reviews, lessons learned, etc. etc. Having all that documentation kept with the project, well organized, is key to "bringing the AI agent up to speed" which you may be doing often. They really do demonstrate the eternal sunshine of the spotless mind, so if you have them take the time to write everything relevant down as they go (not just the code), then when a new one comes online it can jump into the middle of a development plan without repeating (as many) mistakes / making (as many) bad assumptions.

To be brutally honest, working with AI coding agents reminds me a LOT of working with overseas programmer consultants - if you don't get everything in writing you're gonna have a bad time.

Unfortunately your being downvoted by the echo chamber participants that have to make sure you know that your opinion is wrong and theirs is better. AI is a tool, just like my impact gun. Yea there are times where you absolutely should not use an impact gun on something, but it's THE tool for some situations. And yea, using an impact gun where you should t will get you in trouble just like using AI in situations you shouldn't will get you in trouble. There is nothing new on that front!

I've been using it rather heavily since about October of last year, I definitely do notice the models getting better, the tools around the models starting to do some things automatically that I had to manually prompt for last year (especially remembering key instructions). I also believe I am getting better at using them, how much that contributes to my overall results is extremely hard to quantify, but the feeling is definitely there. Like - last October I used to "just ask" for things without having a documented set of requirements. Today, I just know that the requirements document is necessary when the level of complexity is above... well, above a one-off simple example of how to do something relatively trivial.