301–310 of 1001 posts
I’m not shaming but I personally need to know if my sentiment is correct or not or I just don’t know how to use LLMs
Can vibe coder gurus create operating system from scratch that competes with Linux and make it generate code that basically isn’t Linux since LLM are trained on said the source code …
Also all this on $20 plan. Free and self host solution will be best
Earlier quoted context omitted.
This was me. I was a huge AI coding detractor on here for a while (you can check my comment history). But, in order to stay informed and not just be that grouchy curmudgeon all the time, I kept up with the models and regularly tried them out. Opus 4.5 is so much better than anything I've tried before, I'm ready to change my mind about AI assistance. I even gave -True Vibe Coding- a whirl. Yesterday, from a blank dire…
I have a few Go projects now and I speak Go as well as you speak Kotlin. I predict that we'll see some languages really pull ahead of others in the next few years based on their advantages for AI-powered development. For instance, I always respected types, but I'm too lazy to go spend hours working on types when I can just do ruby-style duck typing and get a long ways before the inevitable problems rear their head. N…
Earlier quoted context omitted.
To add to the anecdata, today GPT 5.2-whatever hallucinated the existence of two CLI utilities, and when corrected, then hallucinated the existence of non-existent, but plausible, features/options of CLI utilities that do actually exist. I had to dig through source code to confirm whether those features actually existed. They don't, so the CLI tools GPT recommended aren't actually applicable to my use case. Yesterday…
Were you running it inside a coding agent like Codex? If so then it should have realized its mistake when it tried to run those CLI commands and saw the error message. Then it can try something different instead. If you were using a regular chat interface and expecting it to know everything without having an environment to try things out then yeah, you're going to be disappointed.
A great example of their behaviours for a problem that isn't 100% specified in detail (because detail would need iterations) is available at https://gist.github.com/hashhar/b1215035c19a31bbe4b58f44dbb4....
I gave both Codex (GPT5-ExHi) and Claude (Opus 4.5 Thinking) the exact same prompts and the end results were very different.
The most interesting bit was asking both of them to try to justify why there were differences and then critiquing each other's code. Claude was so good at this - took the best parts of GPTs code, fixed a bug there and ended up with a pretty nice implementation.
The Claude generated code was much more well-organised too (less script-like, more program like).
Earlier quoted context omitted.
I really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. And I get it. Coding with Claude Code really was prompting something, getting errors, and asking it to fix it. Which was still useful but I could see why a skilled coder adding a feature to a complex codebase would just give up Opus 4.5 really is at a…
> Opus 4.5 really is at a new tier however. It just...works. Literally tried it yesterday. I didn't see a single difference with whatever model Claude Code was using two months ago. Same crippled context window. Same "I'll read 10 irrelevant lines from a file", same random changes etc.
Create a markdown document of your task (or use CLAUDE.md), put it in "plan mode" which allows Claude to use tool calls to ask questions before it generates the plan.
When it finishes one part of the plan, have it create a another markdown document - "progress.md" or whatever with the whole plan and what is completed at that point.
Type /clear (no more context window), tell Claude to read the two documents.
Repeat until even a massive project is complete - with those 2 markdown documents and no context window issues.
Most software engineers are seriously sleeping on how good LLM agents are right now, especially something like Claude Code. Once you’ve got Claude Code set up, you can point it at your codebase, have it learn your conventions, pull in best practices, and refine everything until it’s basically operating like a super-powered teammate. The real unlock is building a solid set of reusable “skills” plus a few agents for th…
I really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. And I get it. Coding with Claude Code really was prompting something, getting errors, and asking it to fix it. Which was still useful but I could see why a skilled coder adding a feature to a complex codebase would just give up Opus 4.5 really is at a…
My team is using it with Claude Code and say it works brilliantly, so I'll be giving it another go.
How much of the value comes from Opus 4.5, how much comes from Claude Code, and how much comes from the combination?
I had a similar set of experiences with GPT 5.x over the holiday break, across somewhat more disparate domains: https://taoofmac.com/space/notes/2025/12/31/1830 I hacked together a Swift tool to replace a Python automation I had, merged an ARM JIT engine into a 68k emulator, and even got a very decent start on a synth project I’ve been meaning to do for years. What has become immensely apparent to me is that even gpt…
The thing is that CLI utilities code is probably easier to write for an LLM than most other things. In my experience an LLM does best with backend and terminal things. Anything that resembles boilerplate is great. It does well refactoring unit tests, wrapping known code in a CLI, and does decent work with backend RESTful APIs. Where it fails utterly is things like HTML/CSS layout, JavaScript frontend code for SPAs, a…
But yes, the more specific you get and the more moving pieces you have, the more you need to break things down into baby steps. If you don’t just need it to make A work, but to make it work together with B and C. Especially given how eager Claude is to find cheap workarounds and escape hatches, botching things together in any way seemingly to please the prompter as fast as possible.
Most software engineers are seriously sleeping on how good LLM agents are right now, especially something like Claude Code. Once you’ve got Claude Code set up, you can point it at your codebase, have it learn your conventions, pull in best practices, and refine everything until it’s basically operating like a super-powered teammate. The real unlock is building a solid set of reusable “skills” plus a few agents for th…
I really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. And I get it. Coding with Claude Code really was prompting something, getting errors, and asking it to fix it. Which was still useful but I could see why a skilled coder adding a feature to a complex codebase would just give up Opus 4.5 really is at a…
I had been saying since around summer of this year that coding agents were getting extremely good. The base model improvements were ok, but the agentic coding wrappers were basically game changers if you were using them right. Until recently they still felt very context limited, but the context problem increasingly feels like a solved problem.
I had some arguments on here in the summer about how it was stupid to hire junior devs at this point and how in a few years you probably wouldn't need senior devs for 90% of development tasks either. This was an aggressive prediction 6 months ago, but I think it's way too conservative now.
Today we have people at our company who have never written code building and shipping bespoke products. We've also started hiring people who can simply prove they can build products for us using AI in a single day. These are not software engineers because we are paying them wages no SWEs would accept, but it's still a decent wage for a 20 something year old without any real coding skills but who is interested in building stuff.
This is something I wouldn't have never of expected to be possible 6 months ago. In 6 months we've gone from senior developers writing ~50% of their code with AI, to just a handful of senior developers who now write close to 90% of their code with AI while they support a bunch of non-developers pumping out a steady stream of shippable products and features.
Software engineers and traditional software engineer is genuinely running on borrowed time right now. It's not that there will be no jobs for knowledgable software engineers in the coming years, but companies simply won't need many hotshot SWEs anymore. The companies that are hiring significant numbers of software engineers today simply can not have realised how much things have changed over just the last few months. Apart from the top 1-2% of talent I simply see no good reason to hire a SWE for anything anymore. And honestly outside of niche areas, anyone hand-cracking code today is a dinosaur... A good SWE today should see their job as simply reviewing code and prompting.
If you think that the quality of code LLMs produce today isn't up to scratch you've either not used the latest models and tools or you're using them wrong. That's not to say it's the best code – they still have a tendency to overcomplicate things in my opinion – but it's probably better than the average senior software engineer. And that's really all that matters.
I'm writing this because if you're reading this thinking we're basically still in 2024 with slightly better models and tooling you're just wrong and you're probably not prepared for what's coming.