Summarizer

Something I like about our weird new LLM-assisted world is the number of people I know who are coding again, having mostly stopped as they moved into management roles or lost their personal side project time to becoming parents. AI assistance means you can get something useful done in half an hour, or even while you are doing other stuff. You don't need to carve out 2-4 hours to ramp up any more. If you have significant previous coding experience - even if it's a few years stale - you can drive these things extremely effectively. Especially if you have management experience, quite a lot of which transfers to "managing" coding agents (communicate clearly, set achievable goals, provide all relevant context.)

I'd prefer 1x "wrong stuff" than wrong stuff blasted 1000x. How is that helpful? Further, they can't write code that fast, because you have to spend 1000x explaining it to them.

Which LLMs have you tried? Claude Code seems to be decent at not hallucinating, Gemini CLI is more eager. I don't think current LLMs take you all the way but a powerful code generator is a useful think, just assemble guardrails and keep an eye on it.

They work better with project context and access to tools, so yeah, the web interface is not their best foot forward. That doesn't mean the agents are amazing, but they can be useful.

> That's a polite way of phrasing "they've stolen a mountain of information and overwhelmed resources that humans would use to other find answers." Yes, but I can't stop them, can you? > But I'm glad you're able to have your fun. Unfortunately I have to be practical. > Doubtful. As the arms race continues AI DDoS bots will have less and less recent "training" material. Not a day goes by that I don't discover another site employing anti-AI bot software. Almost all these BigCos are using their internal code bases as material for their own LLMs. They're also increasingly instructing their devs to code primarily using LLMs. The hope that they'll run out of relevant material is slim. Oh, and at this point it's less about the core/kernel/LLMs than it is about building ol' fashioned procedural tooling aka code around the LLM, so that it can just REPL like a human. Turns out a lot of regular coding and debugging is what a machine would do, READ-EVAL-PRINT. I have no idea how far they're going to go, but the current iteration of Claude Code can generate average or better code, which is an improvement in many places.

Why train to pedal fast when we already got motorcycles? You are preparing for yesterday's needs. There will never be a time when we need to solve this manually like it's 2019. Even in 2019 we would probably have used Google, solving was already based on extensive web resources. While in 1995 you would really have needed to do it manually. Instead of manual coding training your time is better invested in learning to channel coding agents, how to test code to our satisfaction, how to know if what AI did was any good. That is what we need to train to do. Testing without manual review, because manual review is just vibes, while tests are hard. If we treat AI-generated code like human code that requires a line-by-line peer review, we are just walking the motorcycle. How do we automate our human in the loop vibe reactions?

> Instead of manual coding training your time is better invested in learning to channel coding agents All channelling is broken when the model is updated. Being knowledgeable about the foibles of a particular model release is a waste of time. > how to test code to our satisfaction Sure testing has value. > how to know if what AI did was any good This is what code review is for. > Testing without manual review, because manual review is just vibes Calling manual review vibes is utterly ridiculous. It's not vibes to point out an O(n!) structure. It's not vibes to point out missing cases. If your code reviews are 'vibes', you're bad at code review > If we treat AI-generated code like human code that requires a line-by-line peer review, we are just walking the motorcycle. To fix the analogy you're not reviewing the motorcycle, you're reviewing the motorcycle's behaviour during the lap.

In practice, I find it depends on your work scale, topic and cadence. I started on the $20 plans for a bit of an experiment, needing to see about this whole AI thing. And for the first month or two that was enough to get the flavor. It let me see how to work. I was still copy/pasting mostly, thinking about what to do. As i got more confident i moved to the agents and the integrated editors. Then i realised i could open more than one editor or agent at a time while each AI instance was doing its work. I discovered that when I'm getting the AI agents to summarise, write reports, investigate issues, make plans, implement changes, run builds, organise git, etc, now I can alt-tab and drive anywhere between 2-6 projects at once, and I don't have to do any of the boring boiler plate or administrivia, because the AI does that, it's what its great for. What used to be unthinkable and annoying context switching now lets me focus in on different parts of the project that actually matter, firing off instructions, providing instructions to the next agent, ushering them out the door and then checking on the next intern in the queue. Give them feedback on their work, usher them on, next intern. The main task now is kind of managing the scope and context-window of each AI, and how to structure big projects to take advantage of that. Honestly though, i don't view it as too much more than functional decomposition. You've still got a big problem, now how do you break it down. At this rate I can sustain the $100 claude plan, but honestly I don't need to go further than that, and that's basically me working full time in parallel streams, although i might be using it at relatively cheap times, so it or the $200 plan seems about right for full time work. I can see how theoretically you could go even above that, going into full auto-pilot mode, but I feel i'm already at a place of diminishing marginal returns, i don't usually go over the $100 claude code plan, and the AIs can't do the complex work reliably enough to be left alone anyway. So at the moment if you're going full time i feel they're the sweet spot. The $20 plans are fine for getting a flavor for the first month or two, but once you come up to speed you'll breeze past their limitations quickly.

So much this. The act of having the agent create a research report first, a detailed plan second, then maybe implement it is itself fun and enjoyable. The implementation is the tedious part these days, the pie in the sky research and planning is the fun part and the agent is a font of knowledge especially when it comes to integrating 3 or 4 languages together.

Look, yeah one shotting stuff makes generic UIs, impressive feat but generic its getting years of sideprojects off the ground for me now in languages I never learned or got professional validation for: rust, lua for roblox … in 2 parallel terminal windows and Claude Code instances all while I get to push frontend development further and more meticulously in a 3rd. UX heavy design with SVG animations? I can do that now, thats fun for me I can make experiences that I would never spend a business Quarter on, I can rapidly iterate in designs in a way I would never pay a Fiverr contractor or three for for me the main skill is knowing what I want, and its entirely questionable about whether that’s a moat at all but for now it is because all those “no code” seeking product managers and ideas guys are just enamored that they can make a generic something compile I know when to point out the AI contradicted itself in a code concept, when to interrupt when its about to go off the rails So far so great and my backend deployment proficiency has gone from CRUD-app only to replicating, understanding and superpassing what the veteran backend devs on my teams could do I would previously call myself full stack, but knowing where my limits in understanding are

Yep, that’s not a bad approach, either. I did that a lot initially, it’s really only with the advent of Claude Code integrated with VS Code that I’m learning more like I would learn from a code review. It also depends on the project. Work code gets a lot more scrutiny than side projects, for example.

I don't like it. It lets "management" ignore their actual jobs - the ones that are nominally so valuable that they get paid more than most engineers, remember - and instead either splash around in the kiddie pool, or go jump into the adult pool and then almost drown and need an actual engineer to bail them out. (The kiddie pool is useless side project, the adult pool is the prod codebase, and drowning is either getting lost in the weeds of "it compiles and I'm done! Now how do I merge and how do I know if I'm not going to break prod?" or just straight up causing an incident and they're apologizing profusely for ruining the oncall's evening except that both of them know they're gonna do it again in 2 weeks). I really don't know how often I have to tell people, especially former engineers who SHOULD KNOW THIS (unless they were the kind of fail-upwards pretenders): the code is not the slow part! (Sorry, I'm not yelling at you , reader. I'm yelling at my CEO.)

Now we ALL be project managers! Hooray!

Amen to that!

Only it’s a bit like me getting back into cooking because I described the dish I want to a trainee cook.

Depends on how you're using the LLMs. It can also be like having someone else around to chop the onions, wash the pans and find the ingredients when you need them.

The head chefs at most restaurants delegate the majority of details of dishes to their kitchen staff, then critique and refine.

This approach seems to have worked out for both Warhol and Chihuly.

So you're saying that if you go to any famous restaurant and the famous face of the restaurant isn't personally preparing your dinner with their hands and singular attention, you are disappointed. Got it.

I would argue that you technically did not cook it yourself - you are however responsible for having cooked it. You directed the cooking.

> If I describe the dish I want, and someone else makes it for me, I was still the catalyst for that dish. It would not have existed without me. So yes, I did "cook" it. The person who actually cooked it cooked it. Being the "catalyst" doesn't make you the creator, nor does it mean you get to claim that you did the work. Otherwise you could say you "cooked a meal" every time you went to MacDonald's.

Why is the head chef called the head chef, then? He doesn’t “cook”.

The difference is that the head chef can cook very well and could do a better job of the dish than the trainee.

"head chef" is a managerial position but yes often they can and do cook.

To differentiate him from the "cook", which is what we call those who carry out the actual act of cooking.

No but I don't use it to generate code usually. I gave agents a solid go and I didn't feel more productive, just became more stupid.

A year or so ago I was seriously thinking of making a series of videos showing how coding agents were just plain bad at producing code. This was based on my experience trying to get them to do very simple things (e.g. a five-pointed star, or text flowing around the edge of circle, in HTML/CSS). They still tend to fail at things like this, but I've come to realize that there are whole classes of adjacent problems they're good at, and I'm starting to leverage their strengths rather than get hung up on their weaknesses. Perhaps you're not playing to their strengths, or just haven't cracked the code for how to prompt them effectively? Prompt engineering is an art, and slight changes to prompts can make a big difference in the resulting code.

I appreciate your reply. A lot of people just say how wonderful and revolutionary LLMs are, but when asked for more concrete stuff they give vague answers or even worse, berate you for being skeptical/accuse you of being a luddite. Your list gives me a starting point and I'm sure it can even be expanded. I do use LLMs the way you suggested and find them pretty useful most of the time - in chat mode. However, when using them in "agent mode" I find them far less useful.

That must be so satisfying. I’ve heard the phrase “code farming” before, but I like the zen garden analogy. If the future is indeed AI, and I’m certainly hearing a lot of people using it extensively, then I think there has to be a mindset shift. Our job will change from craft to damage limitation. Our goal will be to manage a manic junior developer who produces a mixture of good code and slop without architectural level reasoning. Code will rot fast and correctness will hinge on testing as much as you can. It seems like a horrible future. However, it does seem to me that given decades we were unable to build good development practices. Our tooling is terrible. Most of our languages are terrible. Our solution was to let inexperienced devs create languages with all the same flaws, repeating the same mistakes. Web dev is a great example of inefficient software dev that has held the world to ransom. Maybe AI slop is payback for software developers.

Agree, I developed a 150K line stock analytics Saas that started with the will to provide my son with some tools to analyse stocks. I enjoyed this experience of CLI coding so much that I developed Market Sentiment parsing 300,000 business articles and news daily, a dividend based strategy with calendar of payouts and AI optimised strategies to extract every drop of interest, an alert system for a strategy you backtested in the playground and its key triggers are tracked automatically so you can react, an ETF risk analysis model with external factors, all quant graphs and then some, time models with Markov, candlestick patterns, Monte Carlo simulation, walk forward and other approaches I had learned over the years. There is much more. I know you don't measure a project in terms of lines of code, but these are optimised, verified, tested, debugged and deployed. There are so much features, because I was having fun and got carried away. I'm semi-retired and this is like having my web agency back again. I used to program in GRASP... I have a data scientist certification, did a lot of Python, Machine Learning, NLP, etc. I really enjoy the prompt based development process as it seems like you are reaching the right resource for your question from a staff of experienced dev. Of course you need to check everything as a junior dev always creeps in when you least expect it. Especially for security. Discuss best practices often and do your research on touchy subjects. Compare various AI on the same topic. GROK has really caught up. OpenAI has slowed down. CLAUDE is simply amazing. This AI thing is work in progress and constantly changing. I have a noticed an amazing progression over the past year. I have a feeling their models are retrained, tweaked on our interactions even if you asked for them not to use the data. The temptation is too high and the payoffs abound in this market for the best AI tools. I'm building a code factory now with agents and key checkpoints for every step. I want to remove human intervention from multiple sub steps that are time consuming so I can be even more productive in 2026...