HNHacker News
TopNewBestAskShowJobs

noodletheworld

444 karma · joined December 14, 2024

submissionscomments
noodletheworld··on Qwen3.8-Max: A New Bar for Coding and Cowork
> You need to setup a harness that works against your model - You might need to setup additional websearch tools, image tools, etc since harnesses like pi don't come with the model

Pi has a nice guide on it (https://pi.dev/docs/latest/llama-cpp) and it is really not that hard.

How is that hypocrisy? Self hosting is somehow anti AI? Its not anti AI. Its literally using AI!

…and honestly, at a higher technical level than slapping your wallet against a token provider and running prompts in a hosted sandbox you can't even see the prompts in.

noodletheworld··on I regret migrating to Codeberg
That thread is from 2020.

Times change.

Free services owe no one, anything. If you are joining a community, be respectful.

If you're not, and you get banned, that sucks. If it causes a whole category of your peers to be banned that sucks too.

…but its a bit rich to say, oh yeah, the promises you made before LLMs were a thing didn't include a note saying “except if you spam AI generated code”.

Come on.

They dont owe anyone anything.

Certainly not for some comment from ten years ago.

This could entirely legitimately be a case of “was this decision made the right way according to their own decision making process?” … but “is it ok for then to have made this decision?”

Yes. Its fine. It’s their platform. They can do whatever they want.

noodletheworld··on AI Mania Is Eviscerating Global Decision-Making
Look, if they have data and it says 0%, and you have vibes that say that can’t be true, who should we believe?

Do you work with lots of companies and see large AI success stories?

Or do you just vibe that you personally find AI useful so it must also be a business success?

Look, I honestly don’t care, but I think “it must be false” is also unsubstantiated hyperbole. If an agency says they see no AI success, I see no particular reason to believe they’re lying.

They’re not saying AI can’t be a success. They’re saying they haven’t seen it. That matches my experience too. Proven AI success stories seem… vague, when you dig into the details, in my personal experience.

It doesn’t seem surprising to me.

noodletheworld··on Fable turned reMarkable into Tom Riddle's diary from Harry Potter
Whatever man.

If you slap chat GPT on a tablet or a website or a watch or a smart fridge you can make a song and dance about how great it is.

…but bluntly, it would have been impressive 20 years ago.

It is not impressive today; at least, not to me. I’m not 6.

noodletheworld··on Fable turned reMarkable into Tom Riddle's diary from Harry Potter
o_O am I missing something?

Did you show them the github repo, or the disappointing 5 second video of chat gpt from twitter?

I was excited too until I saw it actually running and was like… huh. ChatGPT for tablet. Righto.

What was your son so impressed by?

noodletheworld··on Zuckerberg says AI agent development going slower than expected
> plenty of evidence … although not qualitative or obviously causal

Those two things are the opposite of each other (evidence, but only anecdotally; you cant be both).

Anyway.

More tangible to your argument; what is your argument that this will be more effective than just prompt engineering?

Ive long believed that prompt engineering is a losers game; if there is a trivial set of tricks that improve the output, they will simply be automatically applied.

We see this playing out with the system prompts in coding agents and image gen.

The value of learning “photo realistic studio lighting…” was non existent. The nano banana api is capable of taking a naive prompt and expanding it with these tricks.

People who devoted themselves to learning these “magical incantations” wasted their time and effort; and it was obvious, from the beginning this would be true.

Now.

With managing agents; if a trivial set of management tricks can drastically improve the results, why are you better off learning them now, rather than waiting for them to be baked into cursor/codex/claude in easy mode?

What makes you believe this is a valuable investment in time and effort?

Even if we accept that right now assigning personas to agents and managing them as a manager yields good results, the horizon for change right now is so short, it seems extraordinary to suggest mass management and leadership training for engineers.

We should just wait and see.

All in investments like this would just be tokenmaxing in a funny hat.

noodletheworld··on Jamesob's guide to running SOTA LLMs locally
I sat in a meeting 7 weeks ago where senior leaders said they expect token prices to drop significantly over the next 6 months, and we should all be using as much AI as possible; our team goal was set to use more tokens.

This week, we are banned from using anything more expensive than opus 4.6 and encouraged to use sonnet (but not sonnet 5! Thats expensive!) or lower for daily tasks to help manage costs.

Weeks ago, they gave exactly the same justification as you just gave; and it makes sense!

…but maybe not over the next 6 months.

> Maybe not over the next 18-24 months

Maybe not. Probably not, I guess.

A lot of money has been invested on the expectation that the current gen of hardware is going to reap a colossal profit, and the capex to replace it, is vanishing into investor skepticism as we speak.

It seems like most people have a very very low ability to forecast long horizon change in the current environment, but, in general… it seems like until demand drops, the chances of prices dropping is dubious; at best we get a price war with chinese models or a bubble pop; and even then, there are plenty of startups lurking to snap up cheap hardware.

For individuals, the horizon for buying cheap AI capable compute doesn’t seem close, at all, to me.

noodletheworld··on Vite+ Beta
I appreciate the effort to bring things together in this but…

> Vite+ will manage your global Node.js runtime and package manager.

What? Why?

You’re really going all-in if you adopt this; and… for what? A bit of cozy tooling around existing standard ways of doing things?

Ok, sure; I like tools, like vite.

…but even for an opinionated tool, this is extraordinarily opinionated. Like next.js

Im skeptical.

The pitch of bringing things together seems strong, but did we go too far here?

Reading reviews of people using this didn't really convince me.

It seems to be running on the coat tails of the vite name, rather than its own merit.

noodletheworld··on Tokenmaxxing is dead, long live tokenmaxxing
? What is your point? That the OP is obviously finically motived to encourage tokenmaxing?

Here’s what they said, $$$ aside:

> That’s no longer true. We’ve entered a different regime, where spending more tokens generally results in better results. We call this “compounding correctness” — the more tokens you spend on getting a task correct

> Compounding correctness flips the calculus. If more token spend leads to better outcomes, then you’re going to want to spend a lot of time running tokens. Which sure as hell sounds like tokenmaxxing to me! The original incentives to tokenmax are gone, but eventually folks will realize that a new and more powerful incentive has take its place.

> There were ways to get loops to work, but it was hard. You had to think a lot about how to prompt the agent, which in turn required a pretty deep familiarity with how these things work.

> Now, though, it’s easy. Compounding correctness makes it easy

Go on, tell me I’m quoting the OP out of context.

It’s pretty clear this person believes in compounding correctness, while other, more serious people (1) are perhaps more skeptical.

..and Armins company owns pi. You can’t get much more all in on AI.

Compounding correctness sounds cool, but the real examples of people spending lots of tokens are not compounding correctness; they are wide parallel exploration; like Mythos. The OP is confused, and wrong; they’ve made some basic (flawed) assumptions, and based their entire reasoning on them.

…and are selling AI things. How surprising.

[1] - https://lucumr.pocoo.org/2026/6/23/the-coming-loop/

noodletheworld··on The Coming Loop
Theres a deep insight in this post about the value of looping for throw away code to explore a problem space, rather than brute force a problem by just applying more tokens and hoping.

The more I play in this space, the more I’m drawn to the idea that some kind of back tracking constraint solver is a better solution than then the current naive while loop / brute force approach here.

The results I see are similar to what you get from a greedy brute force constraint solver; solves trivial problems, sometimes solves harder problems after a long time, takes too long to solve really hard problems; solutions are increasingly non optimal on average as complexity goes up.

We have so much existing knowledge about building good constraint solvers, if we could just figure out how to apply it here somehow.

noodletheworld··on The Coming Loop
Use appium or XCTest or swift testing; generate the tests first (failing) from the spec.

The loop is basically then a while loop:

While (tests fail) { trigger agent: spec, failures list }

for bugs, write failing tests.

Its basically TDD.

Loops do nothing useful beyond making the “spec -> code” step more “hands off” and let you be confident that the code you write does what is intended.

Obviously you see the issue: writing the loop harness is > effort than not having it…

…but the idea is that you run “spec first” and are totally hands off on the code, just updating the validation step and then waiting while the agent iterates over and over to solve for some solution that passes the loop harness.

People suggest that it is possible to go, eg. directly figma/jira to harness via (random tool here), saving even more time and invoking even fewer humans, but thats currently, as far as I can tell, actually just hype.

No one is actually doing that effectively.

Loops are currently carefully hand crafted, which makes them tedious and of questionable value imo.

noodletheworld··on You're probably using Agent Skills wrong
Agree; posts like this frustrate me.

Tldr: you're doing it wrong but I will not show you how to do it right. I also did not run the bench using my approach but it definitely “vibes better” to me, and I reject your actual research paper.

Come on, show us some actual skills.

That one you use all the time looks a hell of a lot like “I wont a deterministic shell script for something a skill saying ‘run the shell script’”

Is that what you do? How much time do you spend on them? How do you stop the agent from making a bunch of very similar skills? How do you deal with the explosion of the total number of skills impacting your token use? Do you use skills from github, or is that bad practice? Why?

So many unanswered questions; so little content. :/

noodletheworld··on Hey, n00b, we didn't hire you to complete tasks
> Growing up, in school, I did almost nothing and was consistently at the top of my class

It is clearly widely and indisputably demonstrated that many high achieving children in this situation are failures as adults because they never learn to put effort in.

Terrace tao is on the record writing about his experiences with it, and how it was only his failure in initial college admission shocked him into achieving what he has.

Ie. The point you are making is widely, clearly documented as the naive experience of someone who has not had to achieve at a high level.

> Coaching junior employees to neither ask me for help the instant they're confused nor spin their wheels for two weeks without asking for help is a COMMON thread.

You're a manager. I am sure you have a predictable set of responsibilities, constraints and want a “high performing” team.

Hows that working out for you?

Most advice I, personally, have seen, like this, comes from managers who want to have high performing teams, not ones that have high performing teams.

Its straight out of Be A Manager playbooks.

Whatever, you do you; but, I will emphasise that you are fooling yourself if you believe your experience is universal.

Most very successful people puts lots of effort in.

I… don't know what else to say. If you don't believe that, you are simply, objectively rallying against an extremely large well documented body of knowledge and work on the topic.

noodletheworld··on Hey, n00b, we didn't hire you to complete tasks
This is self-help nonsense your manager will tell you when giving you too much work.

Companies will smartly balance the amount of work allocated to people.

…and then they will push you to take on more work.

High achievers, across the board, consistently demonstrate putting more effort in.

Its just a bitter pill to swallow for some people.

noodletheworld··on Hey, n00b, we didn't hire you to complete tasks
The A signals are not A signals in this article, and this:

> You may be wondering where this “extra” time is going to come from. You’re already committed up to your eyeballs. …We’ll talk about time management, task queue management, diff queue management, and other topics that will accelerate your progress.

Is just corporate dog whistling.

If you are over committed, no amount of time management will solve your problem. Using AI wont solve your problem.

You have a fixed amount of time and too much work?

Work. More. Hours.

Thats the real game; spend extra time outside of your normals hours doing extra.

Congratulations, you’re an “A”.

Makes no difference; your resilience against restructures is not correlated with how much respect you have from senior developers.

That shouldn't be your goal.

There are many places that do what they call “data driven” performance evaluation (translation: avoid being racist by looking only at anonymised numbers) and they do, indeed, look at 40 completed tasks and go: we will keep this one.

The strongest advice for a new starter is: at your specific company ask what you will be reviewed on, and do your best to do whatever that is.

Generic advice is a dime a dozen; don't fall in the trap of assuming [generic advice here] will apply to your specific workplace.

noodletheworld··on Phoenix LiveView 1.2
Many people love liveview.

Many people dislike blazor and it has had its reputation sullied by Microsoft treating it as “new webforms” (yes, they do. It is literally the official migration path for legacy webforms projects).

The pro of blazor, arguably, is c# and the .Net ecosystem.

If I personally had to choose, I wouldn't choose blazor over almost any other technology because I’ve had bad experiences with it.

Technically, they're very similar, but the devexp matters, in my oppinion.

noodletheworld··on Build a Basic AI Agent from Scratch: Long Task Planning
This simply isn't true anymore.

High level generic advice from agents is often, in my experience significantly better, unmodified, than doing nothing.

Obviously its better to do it properly, but you know… opus 4.8 is a pretty great model.

You might be surprised at the quality of the planning, architecture and task breakdown that a simple prompt with some context hints can give you.

…at the end of the day, if I’m working with someone and they give me 6/10 plans based on AI instead of stupid/10 plans they dreamed up, or 0/10 plans they didn't even bother (or in too much of a hurry) to write; Ill take it.

Tragedy of the commons? /shrug

You gotta be pragmatic. It turns subpar contributors into useful contributors.

noodletheworld··on Build a Basic AI Agent from Scratch: Long Task Planning
People get defensive when you ask this, because the they think you’re saying they’re being lazy.

…but it’s than just that (in most cases; I am just lazy sometimes); but fundamentally there’s a limit to how much complexity people can comprehend.

We are good at working at high level abstractions, modules with clear apis that can be sprung to together into some kind of feature.

You don’t need to look inside the black box of the module if you trust the implementer; Ive never opened up the internals of a calendar be like “how does this work?”. I just don’t care. It’s a calendar. I use the api.

I think most people are using these tools in this way; very few people are having an agent write a plan, then a sub agent review it, no human in the loop. Those are for prototypes and are yolo cowboys using open claw and playing with the phones instead of working; we have a few at work, but their PRs are regularly rejected as slop.

…but, realistically; many people aren’t software architects. They may not even know coding patterns, forget architecture patterns.

Having an agent spit out generic software architecture is probably better than what they were producing before.

Writing a module / feature using generic architecture and planning is probably better than random code spaghetti right?

It’s easy to lament the loss of craft here, but at the end of the day, the models today do an ok job of this. The models of tomorrow will probably be better at it than many people.

Architecture is easy composed to actually implementing things. You just wave your hands from your ivory tower and say “more event sourcing”.

noodletheworld··on Replies to comments on my "LLMs are eroding my career" post
Yes; that is literally the opposite of what this article does.
noodletheworld··on Replies to comments on my "LLMs are eroding my career" post
I don't entirely disagree, but as with many other posts on this topic…

> They will come for finance, biology, law, marketing, all knowledge work. That's their stated goal and they're already teasing it with "ChatGPT for Health" and similar launches. They're working on "harnesses" for other fields, it's just a matter of time before we have "Claude Finance Analyst" or something.

…

> Beg to disagree. The models will learn good engineering principles at some point.

…

> Stop and think, don't try to predict the future using (bad) past examples.

Don't try to prediction the future based on the past.

Also, here is my doomsday prediction.

Thats kind of ironic.

Heres a more thoughtful take: everything is an s curve.

Things start out fast, then they slow down.

It happens in learning, in tech, in literally everything.

The question (unanswered) is where we are in that curve.

Will they get better? Yes.

A lot better? A bit better? /shrug

noodletheworld··on Redis 8.8: New array data structure, rate limiter, performance improvements
Why would you embed SQLite?

It’s the same use case with a different api.

A typical (meaningful) example might be communication between threads or actors in a single process, or idempotent tests.

As with SQLite, an external xxx that does this for you is certainly better, etc. but it’s convenient sometimes, to have an application that doesn’t go “now before you run this install Postgres…”.

It’s seldom useful for a web app where you control everything.

noodletheworld··on Nvidia RTX Spark
Yeah but like, Apple put Rosetta 2 out and it was damn good.

Vendors didn’t have to do shit to support the platform, they just got better performance if they did (like factorio).

There is something of a difference between “all your stuff will still work, at comparable performance” and arm windows which (as evidenced by all the vendor promises) you can’t really currently say with prism.

I would describe prism as “surprisingly rubbish considering they had an example of how to do it right” and “your app probably doesn’t run because of drivers or some ??? compatibility thing”.

Am I misremembering? I remember being blown away by Rosetta.

Prism… yeah. Toggle the settings. Disable jit. Disable FP. …bin laptop. Get an intel laptop.

noodletheworld··on MCP is dead?
This is a daft argument.

We have b2b enterprise solutions for sharing text files; we have 1st party, security approved methods for distributing source code that are fundamentally business friendly and compatible with using skills.

MCP might have a place, but claiming it exists because you need a more “enterprise” solution to distributing prompts is just enormously difficult to justify.

(Unless, as the other peer comment indicates, you're not actually trying to make things better or useful, you're trying to sell access to your MCP server. I admit, I take it back; if shilling your company is all you care about maybe MCP is a better option)

noodletheworld··on MCP is dead?
You can share a skill by copy pasting the text file to someone in slack.

Its not that hard.

noodletheworld··on The User Is Visibly Frustrated
Imagine you have a slot machine that consistently gives you 1-5 dollars for every dollar you put in.

You like it.

It feels good, and although you don't win a lot, you consistently win.

…buuut, its a trap.

As you put more money in, the win rate goes down.

You still mostly win when you put 50s in, but it hurts more when you lose, but its still a net gain…

So you start on bigger projects, unsupervised agents, multi agent workflows. You’re dropping 1000s in each time, and…

…and now, you start find yourself shouting at the slot machine.

Its great when it works, but interactions are stressful, because the stakes are higher and fails hurt more.

Screw this, you go back to smaller stakes. Its great.

…but now you're slower, you miss the big wins from big stakes.

So you go back.

…and you get angry. Again. And again. And again… and you’re still kind of winning, and the wins are great but the fails are Super Annoying, because they waste your time, your money, your attention.

It should Just Work but instead why the fuck did you rm -rf my project folder claude?

I think people arent stupid, but we are suckers, and we will dynamically balance the way we use a slot machine tool like this to the very edge of our tolerance for risk and failure.

…and that varies from person to person; but it makes everyone angry when they tip too far and fall into the “repeatedly pull slot machine arm angrily” trap.

Non deterministic tools will always be like this.

It’s like doom scrolling. We’re wired for it. Or at least I am.

noodletheworld··on Microsoft starts canceling Claude Code licenses
Mmm… but for AWS its pay for external use right?

So your costs scale with the number of users you have.

Thats an op ex that you can explain.

For tokens for developers its maybe closer, cost/outcome wise, to hiring an external consulting company to write your code; money paid scales with work done, no promise of delivery, arbitrary unpredictable external price changes.

Its not quite the same; though, similarly lucrative for consultants.

noodletheworld··on The Companies Cutting Headcount for AI Will Lose to the Ones Who Didn't
> kind of

This is arbitrary nonsense.

What “big consultancy” has 5 developers?

What are you even talking about?

noodletheworld··on The Companies Cutting Headcount for AI Will Lose to the Ones Who Didn't
> if the sales pipeline cannot keep everyone busy

That has nothing to do with AI.

It is happening due to global economic conditions.

Im not saying the bench doesn't exist, Im saying its not full of people because you have two consultants doing all 59 jobs with AI.

There are definitely places making cuts of staff who are not on the bench.

noodletheworld··on The Companies Cutting Headcount for AI Will Lose to the Ones Who Didn't
> It isn't as if there are enough projects around to keep the other 2/3 busy, so eventually when there are enough of those people on bench they have to find something else.

Eh, are they doing that though?

Anecdotally, firing people “on the bench” isn't whats happening.

Read the tweets. Listen to people still working at these big corps. They are gutting teams and pushing more work onto people because they believe they can be more productive, not because they are.

Lets that sink in.

People are being made redundant on the basis that leadership believes that in the future they will have an over capacity and theyre cutting early to avoid the bench scenario.

It is speculative.

What this article is arguing, is that, that is stupid.

If, in the future, you need to spin up new initiatives, youve screwed yourself by disposing of your excess capacity in the magical hope that your current capacity will magically increase itself by … spending more money on tokens.

Its just nonsense.

AI is just an excuse for poor historical decisions and unfortunate global economic conditions.

The “cuts due to AI” will be real. There will be people sitting idle as the models improve and people learn to use them better.

… but right now?

they're not. Im not. My friends arent. My former work mates arent. The people left at these companies arent. The people being cut werent (except perhaps, at meta)

Its stock price hype theatre.

noodletheworld··on Show HN: Rmux – A programmable terminal multiplexer with a Playwright-style SDK
I mean, the obvious immediate answer is “windows”, which tmux flat out doesn't support (except via WSL and a shared mount).
← PreviousPage 2 of 8Next →