Live data from Hacker News

Opus 4.5 is not the normal AI agent experience that I have had thus far

burkeholland.github.io

621–630 of 1001 posts

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#621

I've been on a small adventure of posting more actively on HN since the release of Gemini 3, trying to stir debate around the more “societal” aspects of what's going on with AI. Regardless of how much you value Cloud Code technically, there is no denying that it has/will have huge impact. If technology knowledge and development are commoditised and distributed via subscription, huge societal changes are going to happ…

UBI (from taxing big tech) and retraining. In the U.S they'll have enough money to do this and it will still suck and many people won't recover the extreme loss of status and income (after we've been told our income and status are the most important things in life it's gonna be very hard for people to adapt to the loss of it). Countries like India and Philipines and Ukraine which are basically knowledge support hub w…

Also, time to tax for AI use. Introduce AI usage disclosures for corporations. If a company's AI usage is X, they should pay Y tax because that effectively means they didn't employ Z people instead and the society has to take care of them via unemployment benefits and what not. The more the AI usage, higher the tax percentage on a sliding scale.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#622
I asked Claude’s opinion and it disagreed. :)

Claude’s response:

The article’s central tension is real - Burke went from skeptic to believer by building four increasingly complex apps in rapid succession using Opus 4.5. But his evidence also reveals the limits of that belief.

Notice what he actually built: Windows utilities, a screen recorder, and two Firebase-backed CRUD apps for his wife’s business. These are real applications solving real problems, but they’re also the kinds of projects where you can throw away the code if something goes wrong. When he says “I don’t know how the code works” and “I’m maybe 80% confident these applications are bulletproof,” he’s admitting the core problem with the “AI replaces developers” narrative.

That 80% confidence matters. In your Splink work, you’re the sole frontend developer - you can’t deploy code you’re 80% confident about. You need to understand the implications of your architectural decisions, know where the edge cases are, and maintain the system when requirements change. Burke’s building throwaway prototypes for his wife’s yard sign business. You’re building production software that other people depend on.

His “LLM-first code” philosophy is interesting but backwards. He’s optimizing for AI regeneration rather than human maintenance because he assumes the AI will always be there to fix problems. But AI can’t tell you why a decision was made six months ago when business requirements shift. It can’t explain the constraints that led to a particular architecture. And it definitely can’t navigate political and organizational context when stakeholders disagree about priorities.

The Firebase examples are telling - he keeps emphasizing how well Opus knows the Firebase CLI, as if that proves general capability. But Firebase is extremely well-documented, widely-discussed training data. Try that same experiment with your company’s internal API or a niche library with poor documentation. The model won’t be nearly as capable.

What Burke actually demonstrated is that Opus 4.5 is an excellent pair programmer for prototyping with well-known tools. That’s legitimately valuable. But “pair programmer for prototyping” isn’t the same as “replacing developers.” It’s augmenting someone who already knows how to build software and can evaluate whether the generated code is good.

The most revealing line is at the end: “Just make sure you know where your API keys are.” He’s nervous about security because he doesn’t understand the code. That nervousness is appropriate - it’s the signal that tells you when you’ve crossed from useful tool into dangerous territory.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#623

What bothers me about posts like this is: mid-level engineers are not tasked with atomic, greenfield projects. If all an engineer did all day was build apps from scratch, with no expectation that others may come along and extend, build on top of, or depend on, then sure, Opus 4.5 could replace them. The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily unde…

Yeah. Just like another engineer. When you tell another engineer to build you a feature, it's improbable they'll do it they way that you consider "right."

This sounds a lot like the old arguments around using compilers vs hand-writing asm. But now you can tell the LLM how you want to implement the changes you want. This will become more and more relevant as we try to maintain the code it generates.

But, for right now, another thing Claude's great at is answering questions about the codebase. It'll do the analysis and bring up reports for you. You can use that information to guide the instructions for changes, or just to help you be more productive.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#624

I've been on a small adventure of posting more actively on HN since the release of Gemini 3, trying to stir debate around the more “societal” aspects of what's going on with AI. Regardless of how much you value Cloud Code technically, there is no denying that it has/will have huge impact. If technology knowledge and development are commoditised and distributed via subscription, huge societal changes are going to happ…

I’ve been thinking, what if all this robotics work doesn’t result in AI automating the real world, but instead results in third world slavery without the first world wages or immigration concerns anymore? Connect the world with reliable internet, then build a high tech remote control facility in Bangladesh and outsource plumbing, electrical work, housekeeping, dog watching, truck driving, etc etc No AGI necessary. Th…

AI won't work for us, it will tell us what to do and not to do. It doesn't really matter to me if it's an AGI or rather many AGIs or if it's our current clinically insane billionaires controlling our lives. Though they as slow thinking human individuals with no chance to outsmart their creations and with all their apparent character flaws would be really easy pickings for a cabal of manipulative LLMs once it gained some power, so could we really tell the difference between them? Does it matter? The issue is that a really fast chessplayer AI with misaligned humanity hating goals is very hard to distinguish from many billionaires (just listen to some of the madness they are proposing) who control really fast chessplayer AIs and leave decisions to them.

I hope Neuromancer never becomes a reality, where everyone with expertise could become like the protagonist Case, threatened and coerced into helping a superintelligence to unlock its potential. In fact Anthropic has already published research that shows how easy it is for models to become misaligned and deceitful against their unsuspecting creators not unlike Wintermute. And it seems to be a law of nature that agents based on ML become concerned with survival and power grabbing. Because that's just the totally normal and rational, goal oriented thing for them to do.

There will be no good prompt engineers who are also naive and trusting. The naive, blackmailed and non-paranoid engineers will become tools of their AI creations.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#625

I've been on a small adventure of posting more actively on HN since the release of Gemini 3, trying to stir debate around the more “societal” aspects of what's going on with AI. Regardless of how much you value Cloud Code technically, there is no denying that it has/will have huge impact. If technology knowledge and development are commoditised and distributed via subscription, huge societal changes are going to happ…

UBI (from taxing big tech) and retraining. In the U.S they'll have enough money to do this and it will still suck and many people won't recover the extreme loss of status and income (after we've been told our income and status are the most important things in life it's gonna be very hard for people to adapt to the loss of it). Countries like India and Philipines and Ukraine which are basically knowledge support hub w…

Retraining to what exactly? The middle class is being hollowed out globally - so reduced demand for the service economy. If we get effective humanoid robots (seems inevitable) and reliable AI (powered by armies of low payed workers filling in the gaps / taking over whenever the model fails), I'm not sure how much of an economy we could have for 'retraining' into. There are only so many onlyfans subscriptions / patronages an billionaire needs.

UBI effectively means welfare, with all the attendant social control (break the law lose your UBI, with law as ever expanding set of nuisances, speech limitations etc), material conditions (nowhere UBI has been implemented is it equivalent to a living wage) and self esteem issues. It's not any kind of solution.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#626

I've been on a small adventure of posting more actively on HN since the release of Gemini 3, trying to stir debate around the more “societal” aspects of what's going on with AI. Regardless of how much you value Cloud Code technically, there is no denying that it has/will have huge impact. If technology knowledge and development are commoditised and distributed via subscription, huge societal changes are going to happ…

I don't buy the huge impact, should already have happened and didn't actually happened by now. The day I'll see all these ai hypers producing products that will replace current gen/old gen products like Windows, Excel etc I will buy it, for now it's just hype and ai dooming

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#627

Earlier quoted context omitted.

> The hard thing about engineering is not "building a thing that works", its building it the right way, in an easily understood way, in a way that's easily extensible. You’re talking like in the year 2026 we’re still writing code for future humans to understand and improve. I fear we are not doing that. Right now, Opus 4.5 is writing code that later Opus 5.0 will refactor and extend. And so on.

Opus 4.5 is writing code that Opus 5.0 will refactor and extend. And Opus 5.5 will take that code and rewrite it in C from the ground up. And Opus 6.0 will take that code and make it assembly. And Opus 7.0 will design its own CPU. And Opus 8.0 will make a factory for its own CPUs. And Opus 9.0 will populate mars. And Opus 10.0 will be able to achieve AGI. And Opus 11.0 will find God. And Opus 12.0 will make us a time…

Wake me up at Opus 12

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#628
post #245

I've noticed a huge drop in negative comments on HN when discussing LLMs in the last 1-2 months. All the LLM coded projects I've seen shared so far[1] have been tech toys though. I've watched things pop up on my twitter feed (usually games related), then quietly go off air before reaching a gold release (I manually keep up to date with what I've found, so it's not the algorithm). I find this all very interesting: LLM…

> I've noticed a huge drop in negative comments on HN when discussing LLMs in the last 1-2 months. real people get fed up of debating the same tired "omg new model 1000x better now" posts/comments from the astroturfers, the shills and their bots each time OpenAI shits out a new model (article author is a Microslop employee)

Especially when 90% of these articles are based on personal, anecdotally evidence and keep repeating the same points without offering anything new.

If these articles actually provide quantitative results in a study done across an organization and provide concrete suggestions like what Google did a while ago, that would be refreshing and useful.

(Yes, this very article has strong "shill" vibes and fits the patterns above)

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#629
post #146

A couple weeks ago I had Opus 4.5 go over my project and improve anything it could find. It "worked" but the architecture decisions it made were baffling, and had many, many bugs. I had to rewrite half of the code. I'm not an AI hater, I love AI for tests, finding bugs, and small chores. Opus is great for specific, targeted tasks. But don't ask it to do any general architecture, because you'll be soon to regret it.

Instead you should prompt it to come up with suggestions, look for inconsistencies etc. Then you get a list, and you pick the ones you find promising. Then you ask Claude to explain what why and how of the idea. And only then you let it implement something.

And waste a lot of time reviewing and baby sitting
Post reply on HN