It is weird. What does "agent native" mean? This looks like work that requires the use of agents to use properly.
Hence me thinking it is satire. Are we already at a point where libraries and frameworks are being written such that they require agents (from maybe paid frontier models) to properly use?
We live in strange times, if so.
Interestingly, I was just thinking of this problem today: how can I stick with react-like declarative UIs (like one I have developed myself) but yet have them abstracted over native UI frameworks of Apple, Android, even TUIs to produce native apps? What I would have expected is a fully deterministic runtime, compiler, or library approach to solving this, not an agent-driven "solution".
No, there's no requirement to use agents, and others are already building tools for manually working with Construct with a purpose-built editor.
Tools like Hyperframes have already demonstrated the value in catering to agentic-first dev while offering manual inspection and editing interfaces.
Agents aren't equally good at all languages/tools, and just having a lot of training data on one ecosystem isn't enough to optimize the experience. If you read the announcement thread from the CEO there are several points made such as formal safeties against invalid states and build error messages that token-efficiently teach the agent correct usage.
She has not broken any laws nor done anything scummy; what she has done is studied the system and hacked it to her ends: a true hacker in the HN sense of the word.
Now, I hate AI slop as much as anyone can hate it, but if society is so insensitive to actual quality that it will reward slop to the tune of a million dollars, the problem lies with that, not her.
And to her credit, it is not like she is one-shotting books with a single prompt: she has a structured process starting from a human outline and ideas, plus human review at the end.
> Now, I hate AI slop as much as anyone can hate it, but if society is so insensitive to actual quality that it will reward slop to the tune of a millions dollars, the the problem lies with that, not her.
Very true, but perhaps beyond my rapidly expanding misanthropy I can also dislike the process that feeds it. I don’t see it any differently than people disliking companies that push unhealthy and addictive foods, or drug pushers, or any other potential societal malignancy.
Just because we can make the thing and people will buy it doesn’t mean we should make the thing. And the more people that adopt the “lowest common denominator” production process the more we rob ourselves of the joy of creation itself.
Same reason why I'm upset when Temu ships a garbage plastic gadget. Someone must have wanted it, they ordered it, but I doubt that they wanted the quality that showed up. We've all seen the videos of what people think they order vs. what actually shows up. I don't get why you'd go through the trouble of wasting the resources on a scam product, rather than just outright robbing people.
What if the Temu plastic gadget that you ordered actually turns out to be actually quite good and does what you’d expect it too? I think that’s the real comparison here instead of automatically assuming her books are crap that no one enjoys. Obviously enough people enjoy her books (some of it anyway) to make her money.
Are there reviews though? Many readers are always ready to publish reviews of stuff they read, so it's mostly just a matter of finding reviews of works by this author.
First, the societal view on HN-approved hackers is not always positive.
Second, society is bad at recognising systemic problems, that doesn't mean they aren't problems. Something with short term gain for long term harm is a particular problem for our society to handle.
> It is not like she is one-shotting books with a single prompt
It's not clear where she gets the original concept - maybe it's an original idea - fine. But maybe that's another few prompts. Which would make her little more than a meat proxy.
> she has a structured process starting from a human outline and ideas
It's not massively complicated though is it.
> plus human review at the end.
Yeah, it's the proofreaders having to work through hundreds of pages of slop I'm bothered about. Even if you assume the latest models are awesome it's not like this is Astra/frontier output is it?
Complicated enough that very few people have award winning stories. Not even books - you can write 5 great pages and get relatively well known. But apparently it's not that easy.
I created my own declarative react-like UI library that is small, efficient, and does things just the way I want. I have absolutely no desire to go back to the days where for every platform I want to develop for, I need to learn whole new UI paradigm, with all its quirks and gaps and inefficiencies.
Past a certain age, having to do this every year or two get old fast. And, it is not necessary for good performance. The only holding back good performance and capabilities from web apps are the platform vendors.
No, this is the way I have worked for a long time, and I have not suffered from any approval fatigue.
Rather what has happened is that I have gotten very good at scanning what it is trying to do and know within a second or two whether there is anything fishy I need to look at more closely.
And by "fishy", I do not mean only security issues, but also architecture, code, etc issues. Sometimes it even adds unrelated unapproved changes to what it is supposed to be working on, and I stop it.
And I'm glad I work this way, because countless times I have stopped it from going down a path that is nonsensical or I strongly dislike.
There are techniques I have adopted to speed up working this. Sometimes I allow Claude to make larger changes at once, to batch several changes at once, etc. But these decisions are under my control.
I prefer to work this way than to wade through enormous PRs trying to wrap my head around what was done, where I am likely to just give up and approve it after a cursory review.
> Permission rules are old hat. Everyone should be using auto mode instead. It is safer and also does not require manually maintaining finicky allow/deny lists. Auto mode is enabled by default and is included for free in all plans.
More and more it seems we are being prescribed a particular way to use Claude Code: move fast, break things, do not look at the edits, etc. Basically, Claude Code is designed for vibe-coding.
I hate this, and I suspect a lot of devs do too. I use the TUI, and believe it or not, I like to review every edit or change before Claude makes it. I used to allow auto mode and don't ask again sometimes in the past, but now almost never do. The number of incredibly nonsensical things I catch Claude trying to do sometime just reinforced my commitment to this way of working.
So now this idea that permissions are old hat and auto mode is the way to go rubs me the wrong way, very much. And here are a litany of other ways Claude Code TUI is making it hard for me to work:
1. Scroll-back glitches, too numerous to enumerate. Suffice it to say I rely on it a lot, to refer back to something the agent said before, to review the general progression of the session, etc, etc. And it barely works now: missing/overwritten conversation text, messages that have inexplicably disappeared; even sometimes the agent own last response is garbled or hidden or overwritten by some previous message that keeps floating on top.
2. I use iTerm2 on macOS, and frequently use split panes. Whenever change the width of a pane, Claude Code messes up the conversation text so that is often unreadable, and nothing I do will restore it.
3. As other sibling comments have noted, the current preference of Claude to use incomprehensible scripts for editing files is off-putting and a hindrance to being in control of my work. I have resorted to using the permissions setting to ban it from using Go, Perl, Python, and sed (for in pace editing), etc, to cope with this.
4. Even basic text editing is messed up in Claude Code TUI. I used to be able to navigate around lines effectively by using up/down keys; this was removed, which has significantly impacted by work. I cannot disable copying on selection, which I don;t want, because if I disable it, the copying does not work at all, etc
At this point, due to all the impediments Claude Code places to my style of working, the only reasonable conclusion I can reach is: I am supposed to be vibe coding, letting the agents loose to vomit out massive amounts of slop. But if vibe coding of the Claude Code TUI itself is producing such garbage, why should anyone be convinced that it is a good thing?
I will never let Claude Code loose to do its thing; I will not surrender my control to it, no matter how much many times I hear I no longer need to look at code.
Oh those were the days, I remember developing my first non-trivial piece of software (an international checkers game), while still a student, with Turbo Pascal. It run to more than a thousand lines of basically the Minimax algorithm plus various optimizations (alpha beta pruning, quiescent extensions, etc)
I have fond memories of the language, the IDE, libs like TurboVision, ObjectWindows, etc... And fun times with the demos TVChess and OwlChess, which gave me inspiration.
Wow man, "horrific code" can be worse than no code. Bad code can damage hardware, destroy data, allow exploits, etc. all manner of bad things.
Unless your meaning is that you already have work-in-progress code that you are working on to make much better whereas they have not even started, I don't see how your point makes sense.
But even then it debatable whether making bad code good is better than creating good code from the start.
I thought LLMs were supposed to be the death knell for services like this, since you could replicate them and maintain your own code-base with little effort?
The thing that separates feature flags from “why not vibe it” is reliability. Flags going down can take everything down, so you really ought get the most reliable system you can. That means multi-cloud deployment and good thought as to failover. Secondarily, flags really benefit from some good telemetry to understand what is being used and that expands scope as well. Oh and SDK that are really good under various failure conditions.
What AI dev is doing to this space is commoditizing it, not replacing it. Prices for the crystallized judgment of these tools will fall to near compute. But that still doesn’t mean you ought burn tokens to get an inferior solution to what’s available off a shelf.
Many controls don't work well. Might be better to focus on a few games and make dedicated UIs for them that are adapted to each game.
I guess it is a nice introduction to street games in Ghana though.
reply