I would say it is reasonably clear they had already committed to rewriting at that point.

The possibility that that particular code might be thrown out was potentially true, but also totally unrelated to the previous statement.

At the end of the day, whatever, but this feels a heck of a lot like “ah, we didn't mean for this to be public yet” rather than “this is just a random experiment”.

AI companies love AI stories.

It is an AI company.

:p

[1] - https://news.ycombinator.com/item?id=48016880

And what? Just let the actor just keep using them to spread to other people?

Always rotate your tokens immediately if they're compromised.

If it hurts, well, that sucks. …but seriously, not revoking the tokens just makes this worse for everyone.

A fair comment would have been: “it looks like the payload installs a dead-mans switch…”

Asking the maintainers not to revoke their compromised credentials deserves every down vote it receives.

Yes.

That is how you empirically evaluate tools; not by reading stupid benchmarks. By actually using the tools, for hours and hours. Doing real work.

Did you try using it? For hours? Do you use qwen?

How about you tell us about your experience with your great 8B models that you use daily. What coding agent harness do you have then hooked up to? What context size can you get before they lose track of whats happening? Do you swap between models for different coding tasks?

Or, have you not, actually, even actually tried any of this stuff, yourself?

Qwen is really good.

Also, generally, it makes sense. 8B models are generally not very good^.

That this 8B model is decent is impressive, but that it could perform on par with a good model 4 times as large is a daydream.

^ - To be polite. The small models + tool use for coding agents are almost universally ass. Proof: my personal experience. Ive tried many of them.

> it picked up the general path immediately

I said:

> Or they have spent a lot more time and effort on it than they claim.

You said:

> You imply I'm merely "pointing CC at godot and it made a game"; I never said it was simple

Well. I dont care enough to argue with you, but Im not the one being contrary here.

Readers can google “claude with godot” for a guide on setting it up and decide if that counts as picking it up immediately or not, and if what you said is honest, or hype.

What I said is not that I dont believe youre using claude; but that I roll my eyes at the unbounded enthusiasm for using AI agents with the magical pretence that its easy and productive straight away.

Its not.

Your post gave the impression that it is.

That makes me roll my eyes.

> But I had already answered, before your comment, with screenshots

> Of course these are basic placeholders for a few hours of work

Lord, spare me. You spent a few hours vibing and came to the conclusion that everything is golden?

…and yet you have a:

> I do have a careful setup involving CI and isolation.

So what, you spent more time on your setup than actually coding before posting?

/shakes-head

Whatever man.

Have fun. I stand by what I posted before.

…and yet, most people continue to say that non standard tooling ecosystems, where the agent cannot run and validate the code it writes, remain difficult and unproductive.

“I just pointed CC at godot and it made a game! This is sooo good”

…is a fairytale.

What tooling are you using to make it run and compile the code? How is it iterating on the project without breaking existing functionality?

None of these are insurmountable, but they require some careful setup.

Posts like this dont make me laugh; they just make me roll my eyes.

Either the OP has not done what they claim.

Or they have spent a lot more time and effort on it than they claim.

> I gave him game design ideas, he comes with working code. I gave him papers about procedural algos, and he comes with the implementation, brainstorm items, create graphic assets (he created a set of procedural 2d generators as external tools), he even helped me build the lore.

Such a sweet story about a boy and his AI.

Unfortunately, I also dont believe in fairytales.

Instead of waving your hands wildly about AI, post some videos and code of the results.

This is hackernews, not hypenews.

I desperately hate that modern tooling relies on “did you perform the correct prayer to the Omnissiah”

> to add some entropy to get it away from the local optimum

Is that what it does? I don't think thats what it does, technically.

I think thats just anthropomorphizing a system that behaves in a non deterministic way.

A more menaingful solution is almost always “do it multiple times”.

That is a solution that makes sense sometimes because the system is prob based, but even then, when youre hitting an opaque api which has multiple hidden caching layers, /shrug who knows.

This is way I firmly believing prompt engineering and prompt hacking is just fluff.

Its both mostly technically meaningless (observing random variance over a sample so small you cant see actual patterns) and obsolete once models/apis change.

Just ask Claude to rewrite your request “as a prompt for claude code” and use that.

I bet it wont be any worse than the prompt you write by hand.

Mmm. Very nice.

Explicitly avoiding turning react into “webforms” and focusing on the actual point of RSC seems like the path RSC should have had from the beginning.

Magical RPC so you could “use server” and not bother to write an API properly was never the point of RSC, and the CVEs showed why it was a bad idea.

This is an unusually hostile take.

The authors comment about address instability is only a minor point in the article:

> happylock also sorts locks by memory address, which is not stable across Vec reallocations or moves.

…specifically with regard to happylock, which has a bunch of commentary on it (1) around the design.

You're asserting this is a problem that doesn't exist in general, or specifically saying the author doesn't know what they're talking about with regard to happylock and vecs?

Anyway, saying they're not competent feels like a childish slap.

This is a well written article about a well written library.

Its easy to make a comment like this without doing any research or actually understanding whats been done, responding to the title instead of the article.

Specifically in this regard, why do you believe the approach taken here to overcome the limitations of happylock has not been done correctly?

(1) - https://github.com/botahamec/happylock

So does an API and a text file (or hell, a self describing api).

Which is more complex and harder to maintain, update and use?

This is a solved problem.

The world doesnt need MCP to reinvent a solution to it.

If we’re gonna play the ELI5 game, why does MCP define a UI as part of its spec? Why does it define a bunch of different resource types of which only tools are used by most servers? Why did not have an auth spec at launch? Why are there so many MCP security concerns?

These are not idle questions.

They are indicative of the “more featurrrrrres” and “lack of competence” that went into designing MCP.

Agents, running a sandbox, with normal standard rbac based access control or, for complex operations standard stateful cli tooling like the azure cli are fundamentally better.

Nope.

The best way to interact with an external service is an api.

It was the best way before, and its the best way now.

MCP doesn't scale and it has a bloated unnecessarily complicated spec.

Some MCP servers are good; but in general a new bad way of interacting with external services, is not the best way of doing it, and the assertion that it is in general, best, is what I refer to as “works for me” coolaid.

…because it probably does work well for you.

…because you are using a few, good, MCP servers.

However, that doesn't scale, for all the reasons listed by the many detractors of MCP.

Its not that it cant be used effectively, it is that in general it is a solution that has been incompetently slapped on by many providers who dont appreciate how to do it well and even then, it scales badly.

It is a bad solution for a solved problem.

Agents have made the problem MCP was solving obsolete.

It’s not a rust ui system; it’s a declarative ui language that happens to have a rust binding via macros so you can write the custom DSL.

It also has bindings for other languages.

It feels like a bunch of qtquick people got together and implemented a new runtime for qtquick. That might be the direction qt has gone, at the expense of their c++ qtwigets system, but it just feels… “electron app” to me.

If I wanted an electron app, I would just use electron.

If I wanted a non-native ui look and feel, I would use flutter.

Is a fantasy you invented to argue against.

Microsoft’s 1st party offerings are an embarrassment.

Apples first party offering isnt amazing either; it’s just “ok”; but its not a total embarrassment.

There are just more people encountering them because the developers are concentrated on using one thing.

It’s not perfect, but a compared to Microsoft, calling Apple out for having bugs is a little rich isn't it?

I pose to you, if the Microsoft offerings are so compelling, why are the serious players using 3rd party wrappers like QT and Avalonia?

It’s because the first party offerings are not compelling. They’re a disaster dumpster fire. And buggy.

The OP is fundamentally expressing the opinion that single task threads are easier to keep track of.

Agree / disagree? Sure.

…but dipping into pedantry about terms (swarm, subagent, vine coding, agentic engineering) really doesn't add anything to the conversation does it?

You said:

> I think you misunderstand "swarms of agents", based on what you say above.

…but from reading the entire post I am pretty skeptical anyone was confused as to what they meant.

Wrong term? Don't care. If someone calls it a hallucination? Also don't care.

That cursor is focusing on “do stuff in parallel guys!”? Yeah, I care about that.

> it is probably best not to use that word if you are referring to multiple agents working on multiple tasks, right?

Not relevant to the thread. Also, I work with people who casually swap between using these exact words to mean both things.

I donnnt caarrrrre what people call it.

…when the meaning is obvious from the context, it doesnt matter.

How can multiple parallel agents some local and some in the cloud be working on a single task?

How can:

> All local and cloud agents appear in the sidebar, including the ones you kick off from mobile, web, desktop, Slack, GitHub, and Linear. (From the announcement, under “Run many agents in parallel”)

…be working on the same task?

Subagents are different, but the OP is not confused about what cursor is pushing, and it is not what you describe.

Its always hard to really trust these corporate funded open source products, but they've honestly been great.

…but I find it difficult to believe openai owning the corner stone of the python tooling ecosystem is good thing for the python ecosystem.

There is no question openai will start selling/bundling codex (and codex subscriptions) with uv.

I dont think I want my package manger doing that.

The system is clearly resolving the users query.

Mixing that with the deterministic “play the songs requested instead of random crap” or even “play related classical music instead of random crap” is clearly not an impossibility.

It actually almost did the right thing. …but no, rather than handling the difficult edges cases like this, just do whatever for edges cases.

It is lazy.

Handling complex difficult edge cases is what differentiates good products from lazy ones.

There is no confusion as to which “AI” the OP is referring to.

The author wrote:

> Or does the AI work in so mysterious a way that the programmers need no longer take responsibility?

They are pondering, in general, if the non deterministic nature of AI is an excuse for bad products.

The Spotify DJ is a recommendation engine.

Its bad.

Its a lazy, bad implementation that relies on AI, instead of deterministic algorithms; eg. identify requested music and play it.

Instead it wants to “try something different”.

If you press play on the music player on your phone, do you expect it to “try something different?”

…or, is AI making developers and product managers lazy?

It is not a complicated take, and the example is, to me, pretty compelling.