HNHacker News
TopNewBestAskShowJobs

noodletheworld

444 karma · joined December 14, 2024

submissionscomments
noodletheworld··on DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
> And most importantly, you modify the work just like the creators modify the work

Emphasis mine.

Weights are not open source.

You can define terms to mean whatever you want, but fundametally if you cannot modify the “output” the way the original creators could, its not in the spirit of open source.

Isnt that literally what you said?

How can you possibly claim both that a) you can modify it the creators did, b) thats all you need to be open source, but…

Also c) the categorically incorrect assertion that the weights allow you to do this?

Whatever, I guess, but your argument is logically wrong, and philosophically flawed.

noodletheworld··on AI Adoption Rates Starting to Flatten Out
Skill declines over time, without practice.

If you speak fluent japanese, and you dont practice, you will remember being fluent but no longer actually be able to speak fluently.

Its true for many things; writing code is not like riding a bike.

You cant not write code for a year and then come back at the same skill level.

Using an agent is not writing code; but using an agent effectively requires that you have the skill of writing code.

So, after using a tool that automatically writes code for you, that you probably give some superficial review to, you will find, over time, that you are worse at coding.

You can sigh and shake your head and stamp your feet and disagree, but its flat out a fact of life:

If you dont practice, you lose skill.

I, personally found, this happening, so I now do 50/50 time: 1 week with AI, 1 week with strictly no AI.

If the no AI week “feels hard” then I extend it for another week, to make sure I retain the skills I feel I should have.

Anecdotally, here at $corp, I see people struggling because they are offloading the “make an initial plan to do x that I can review” step too much, and losing the ability to plan software effectively.

Dont be that guy.

If you offload all your responsibilities to an agent and sit playing with your phone, you are making yourself entirely replacable.

noodletheworld··on Pocketbase – open-source realtime back end in 1 file
Hmmm… firebase clones are many and varied.

Whats special about this one?

Being a single file binary doesnt impress me; thats true of many projects in many langauges.

It seems nice you can use it as a go framework if you happen to use go, but Im not really compelled by the “it doesn't scale at all” aspects of it.

Someone whos used some other similar stuff comment on why this over any of the others, eg. self hosted superbase?

noodletheworld··on Migrating the main Zig repository from GitHub to Codeberg
> I just don't like how they have to put out false claims like there are big problems with GH CI and Sponsors

These aren't false claims.

Thats my point.

Microsoft can afford to make these tools better; they just dont care.

Yes, its better than having nothing, but honestly you have to be wearing blinkers not to see the decline rn.

noodletheworld··on Migrating the main Zig repository from GitHub to Codeberg
Oh come on.

Micros$$$$ft owns github.

We don't need to give some pretend sympathy.

When you can afford to have good things, and you're not, don't come crying about getting called bad names.

Actions is bad.

> I dare anyone who is delusional enough to think they can create something better to actually make something better

Actions speak louder than words.

Zig is leaving because of the issues they mentioned.

> People tried other services like GitLab and realized it is slower, uglier and overall worse than GH and came crawling back.

Maybe. I guess we'll see.

I think the OP has been pretty clear that they're not happy with it, and, they're putting their money where their mouth is.

Clearly, just complaining about broken things isn't working.

Maybe a couple more big moves like this is what GH needs to wake up and allocate some more resources (that they, can categorically afford) to fixing things.

noodletheworld··on Claude Advanced Tool Use
> I never really understood why you have to stuff all the tools in the context.

You probably don't for... like, trivial cases?

...but, tool use is the most fine grained point, usually, in an agent's step-by-step implementation plan; So when planning, if you don't know what tool definitions exist, an agent might end up solving a problem naively step-by-step using primitive operations, when a single tool already exists that does that, or does part of it.

Like, it's not quite as simple as "Hey, do X"

It's more like: "Hey, make a plan to do X. When you're planning, first fetch a big list of the tools that seem vaguely related to the task and make a step-by-step plan keeping in mind the tools available to you"

...and then, for each step in the plan, you can do a tool search to find the best tool for x, then invoke it.

Without a top level context of the tools, or tool categories, I think you'll end up in some dead-ends with agents trying to use very low level tools to do high level tasks and just spinning.

The higher level your tool definitions are, the worse the problem is.

I've found this is the case even now with MCP, where sometimes you have to explicitly tell an agent to use particular tools, not to try to re-invent stuff or use bash commands.

noodletheworld··on MCP Apps: Extending servers with interactive user interfaces
An, the dream, a cross platform App Store you can install apps into any client application that supports MCP, but is open, free and agentic.

It’s basically a “web App Store” and we side step the existing app stores (and their content guidelines, security restrictions and billing requirements) because it’s all done via a mega app (the MCP client).

How could it go wrong?

If only someone had done this before, we wouldnt be stuck in Apples, etc’s walled gardens…

Seriously though; honest question: this is literally circumventing platform requirements to use the platform app stores. How do you imagine this is going to be allowed?

Is ChatGPT really big enough they can pull the “we’re gonna do it, watcha gonna do?” to Apple?

Who’s going to curate this app store so non technical users (the explicitly stated audience) can discover these MCP apps?

It feels like MCP itself; half baked. Overly ambitious. “We’ll figure the details out later”

noodletheworld··on Maybe you’re not trying
Hm.

Its an easy trap to fall into to say that people are in hard situations because They Arent Trying Hard Enough.

Your manager might think so.

Your company probably thinks youre not trying hard enough.

…but, there is a also reality, which is overloading people with impossible expectations and then watching them fail isnt helpful.

Its not a learning experience.

Its just mean, and selfish… even when those expectations are, perhaps, self imposed.

If youre in one of these situations, you should ask for help.

If you see someone in them, you should offer to help.

Its well documented that gifted children struggle as adults because they struggle under the weigh of expectations.

The soltuion to this is extremely rarey self reflection about not trying hard enough.

Geez. Talk about setting people up for failure.

The OP literally succeeded by asking for help, yet somehow, walked away with no appreciation of it.

noodletheworld··on URLs are state containers
Mmm.

Youre doing two things:

1) youre moving state into an arbitrary untrusted easy to modify location.

2) youre allowing users to “deep link” into a page that is deep inside some funnel that may or may not be valid, or even exist at some future point in time, forget skipping the messages/whatever further up.

You probably dont want to do either of those two things.

noodletheworld··on How I use every Claude Code feature
Claude is just better at coding than cursor.

Really, the interface isn't a meaningful part of it. I also like cmd-L, but claude just does better at writing code.

...also, it's nice that Anthropic is just focusing on making cool stuff (like skills), while the folk from cursor are... I dunno. Whatever it is they're doing with cursor 2.0 :shrug:

noodletheworld··on I'm drowning in AI features I never asked for and I hate it
Hot take: it’s not just “me too! Valuation pls”.

Tokens are fine grained billable attribute that lets you add micro transactions to your service.

Not in all cases, but in many we exist in a complicated world of enshitifcation + inflation.

Inflation means you need to somehow make more money.

You can either: raise prices (unpopular), make your product cheaper (unpopular) or add new features and rise the price on the basis of “new value!”.

You see major organisations doing this: same product, but now with ai! …and it’s more expensive. Or it’s a mandatory bundle. Or it’s “premium”.

Long storm short, a lot of companies see the way that cloud providers do billing (usage based billing, no caps, you get the bill after using it) as the ideal end state.

Token based billing moves towards that world; which isn’t just “profit!” …it’s companies trying to deal with the reality of a complicated market place that will punish them for raising prices.

…and it is bad. I’m just saying that it’s kind of naive to think so many companies are doing this just as a “me tooooo!”. Come on; even if you’re hunting a funding round, the people running these companies are (mostly) not complete idiots.

No one is adding AI features because it’s fun, or they’re bored.

…

…ok, there are some idiots. Most people have a bigger vision for these features than just annoying their users.

noodletheworld··on Reasoning LLMs are wandering solution explorers
The important argument in this paper is:

> We argue that systematic problem solving is vital and call for rigorous assurance of such capability in AI models. Specifically, we provide an argument that structureless wandering will cause exponential performance deterioration as the problem complexity grows, while it might be an acceptable way of reasoning for easy problems with small solution spaces.

Ie. thinking harder still samples randomly from the solution spaces.

You can allocate more compute to the “thinking step”, but they are arguing that for problems with a very big solution space, adding more compute is never going to find a solution, because you’re just sampling randomly.

…and that it only works for simple problems because if you just randomly pick some crap from a tiny distribution you’re pretty likely to find a solution pretty quickly.

I dunno. The key here is that this is entirely model inference side. I feel like agents can help contain the solution space for complex problems with procedural tool calling.

So… dunno. I feel kind “eh, whatever” about the result.

noodletheworld··on The React Foundation
> vercel is a company which is heavily invested in

…people paying for react.

Which is fair, but do we have bend knee and suggest they have the best interests of the react ecosystem at heart? They don’t.

They are invested in: people using next.js and hosting it on vercel.

If that’s not what you’re doing, their interests probably don’t align with yours.

noodletheworld··on Being blocked from contributing to lodash
If someone opens a PR to one of my repos with no context, I ban them.

There’s too much AI spam out there right now.

Publishing ‘@provenance-labs/lodash’ as a test, I suppose. Ok. Leaving it up? Looks like spam.

Badgering the author an a private email? Mmm. Definitely not.

This isn’t a bug, it’s a feature. There’s a contributing guide which clearly says; unless a feature gets community interest, it’s not happening. If you want a feature, talk about it rouse community interest.

Overall: maybe this wasn’t the right way to engage.

Sometimes you just have to walk away from these situations, because the harder you chase, the more it looks like you’re in the wrong.

…it certainly looks, right now, like the lodash author wasn’t out of line with this, to me.

noodletheworld··on Cursor 1.7
It’s obviously farcical.

Anyone seriously using these tools knows that context engineering and detailed specific prompting is the way to be effective with agent coding.

Just take it to the extreme and youll see; what if you auto complete from a single word? A single character?

The system youre using is increasingly generating some random output instead of what you were either a) trying to do, or b) told to do.

Its funny because its like, “How can we make vibe coding even worse?”

“…I know, lets just generate random code from random prompts”

There have been multiple recent posts about how to direct agents using a combination of planning step, context summary/packing, etc to craft detailed prompts that agents can effectively action on large code bases.

…or yeah, just hit tab and go make a coffee. Yolo.

This could have been a killer feature about using a research step to enhance a user prompt and turn it into a super prompt; but it isnt.

noodletheworld··on How HubSpot scaled AI adoption
If someone wants to pat themselves on the back with how great they think they are, thats cool, but I dont think its really worth talking about.

…unless they have something to show, specifically?

Demos? Code? Details?

Nothing?

noodletheworld··on Getting AI to work in complex codebases
> sometimes

Mhm. Money -> to the dealer.

Anyway… watch the videos the OP has of the coding live streams. Thats the most interesting part of this post: actual real examples of people really using these tools in a way that is transferable and specifically detailed enough to copy and do yourself.

noodletheworld··on Getting AI to work in complex codebases
You didnt have 10 of them running though.

You want to do that, but Ill bet money you arent doing it.

Thats the problem: this is speculative; maybe it scales sometimes, but mostly people do not work on ten things at once.

“Fix the landing page”

“I’ll make you ten new ones!”

“No. Calm down. Fix this one, and do it now, not when youre finished playing with your prompts”

There are legitimate times when complex pieces of work decompose into parallel tasks, but its the exception not the norm.

Most complex work has linked dependencies that need to be done in order.

Remember the mythical man month? Anyone? Anyone???!!??

You can't just add “more parallel” to get things done faster.

noodletheworld··on Kevo app shutdown
I unironically look forward to the world where this is solved by unsupervised AI agents incrementally upgrade these apps to keep them evergreen...

...and the Lovecraftian gradual drift as incremental recursive hallucinations turn them into still... mostly working... strange little app-like-bundles of Something Weird.

noodletheworld··on iTerm2 Web Browser
Mmm… no.

Iterm2 used to be one if my first installs, but these days I find myself in the old grumpy programmer bucket.

Things that should connect to the internet:

- my browser

- applications

- anything I explicitly launch

Things that should not connect to the internet:

- my shell

- my “save as” dialog

- my start menu

:(

> Click hamburger menu → Ask AI to create a new AI chat with the reader-mode content of the current page attached

Yeah yeah cool.

I guess were back into the days of more web browsers with arc and whatever.

I suppose I should just smile and nod; if chrome introduced a terminal would I batt an eyelid?

Still, I dont like it.

I dont want ls to query some external api.

I dont want grep to search the internet.

These these are domain bounded for a reason; Im not a fan of iterms kitchen sync future.

…but I suppose, nice technical work on it, it works quite well. I hope it makes people who are into it happy.

noodletheworld··on Waymo has received our pilot permit allowing for commercial operations at SFO
Hey, Im a fan. Fail fast. Build things.

Most very rich people just sit and roll in their money in the finance markets like scrooge mcduck.

But… I think the performance in the whitehouse was performative nonesense.

What a waste of everyone’s time for the sake of appearances.

More building things, less dancing please Elon.

noodletheworld··on React is winning by default and slowing innovation
Jquery is the old default for web apps from before people decided they wanted react.

What can it do that others cant? Literally nothing.

That didnt and does not stop it from being used for connivence sake.

The point is: if its not about the technical quality; why are we not still using it now?

noodletheworld··on React is winning by default and slowing innovation
Then why dont you pick jquery?

Its easy and well known, even now.

The answer I see is that react is technically good enough.

Using boring technology doesnt mean using the technically most advanced thing.

It means picking something safe and stable.

noodletheworld··on AI coding
I think the key insight I walked away with from this whole thread, for me, was:

A compiler takes source and maps it to some output. Regardless of the compiler detail, this is an atomic operation; you end up with source (unmodified) and an artifact.

These “agent workflows” are distinctly different.

The process of mapping prompt to an output is the same; but these agent workflows are destructive; they modify the source.

Free reign over the entire code base; They modify the tests. The spec, the implementation.

It seems like this is a concept people are still struggling with; if your specification is poorly defined, and is dynamically updated during the compilation process, the results are more than just non deterministic.

Over time, the specification becomes non deterministic.

Thats why unsupervised agents go “off the rails”; not because the specification cant be executed, but because over time the spec drifts.

That doesnt happen with compilers.

noodletheworld··on How to use Claude Code subagents to parallelize development
No, this has been my experience as well.

I see lots of people saying you should be doing it, but not actually doing it themselves.

Or at least, not showing full examples of exactly how to handle it when it starts to fail or scale, because obviously when you dont have anything, having a bunch of agents doing any random shit works fine.

Frustrating.

noodletheworld··on EU court rules nuclear energy is clean energy
Oh come on.

I consider myself reasonably pro nuclear, but this is just like some developer going:

“Oh yeah, that doesn't seem that hard, I could probably implement that in a weekend”

Fact: hard complicated things are expensive.

There is no “just it’s just some concrete…”.

That is, translated “I do not know what Im talking about”.

Hard things, which require constant, high level, technical maintenance…

Are very expensive.

Theyre expensive to build. Theyre expensive to operate. Theyre expensive to decommission.

Theres no magic wand to fix this.

You can drive down the unit cost sometimes by doing things at scale, but Im not sure that like 100 units, or even say 1000 units can do that meaningfully.

…and how how are we planning on having the 100000s of reactors that you would need for that?

Micro reactors? Im not convinced.

Certainly, right now, the costs are not artificial; if you think they are, I would argue you havent done your due diligence in research.

Heres the point:

Making complicated things cheaper doesnt just magically happen by removing regulations. Thats naive.

You need a concrete plan to either a) massively simplify the technology or b) massively scale the production.

Which one? (a) and (b) both seem totally out of reach to me, without massive state sponsored funding.

…which, apparently no one likes either.

Its this frustrating dilemma where idiots (eg. former Australian government) claim they can somehow magically deliver things (multiple reactors) super cheaply.

…but there is no reality to this promise; its just morons trying to buy regional votes and preserve the status quo with coal.

Real nuclear progress needs realistic plans, not hopes and dreams.

Nuclear power is better; but it is more expensive than many other options, and probably, will continue to be if all we do is hope it somehow becomes easy and cheap by doing basically nothing.

noodletheworld··on The Last Programmers?
It would be fresh, just now and then to see a passionate AI bro who isn’t selling AI.

You know, I get it, earn those clicks. Spun that hype. Pump that valuation.

Now, go watch people on YouTube like Armin Ronacher (just search, you’ll find him), actually streaming their entire coding practice.

This is what expert LLM usage actually looks like.

People with six terminal running Claude are a lovely bedtime story, but please, if you’re doing it, do me a favour and do some live streams of your awesomeness.

I’d really love to see it.

…but so far, the live coding sessions showing people doing this “everyday 50x engineer” practice don’t seem to exist, and that makes me a bit skeptical.

noodletheworld··on Where's the shovelware? Why AI coding claims don't add up
> people are going to get a variety of results.

Yes, but the point of this article is surely that on average if it's working, there would be obvious signs of it working by now.

Even if there are statistical outliers (ie. 10x productivity using the tools), if on average, it does nothing to the productivity of developers, something isn't working as promised.

noodletheworld··on Do the simplest thing that could possibly work
Really?

We both read the article; you know as well as I do that the advice in it is to build simple reliable system that focus on actual problems not imagined ones.

…but does not say how to do that; and offers no meaningful value for someone trying to pick the “right” thing in the entire solution space that is both sufficiently complex and scalable to solve the requirements, but not too scalable, or too complex.

There’s just some vague hand waving about over engineering things at Big Corp, where, ironically, scale is an issue that mandates a certain degree of complexity in many cases.

Here’s some thing that works better than meaningless generic advice: specific detailed examples.

You will note the total lack of them in this article, and others like it.

Real articles with real advice are a mix of practical examples that illustrate the generic advice they’re giving.

You know why?

…because you can argue with a specific example. Generic advice with no examples is not falsifiable.

You can agree with the examples, or disagree with them; you can argue that examples support or do not support the generic advice. People can take the specific examples and adapt them as appropriate.

…but, generic advice on its own is just an opinion.

I can arbitrarily assert “100% code coverage is meaningless; there are hot paths that need heavy testing and irrelevant paths that do not require code coverage. 100% code coverage is a fools game that masks a lack of a deeper understanding of what you should be testing”; it may sound reasonable, it may not. That’s your opinion vs mine.

…but with some specific examples of where it is true, and perhaps, not true, you could specifically respond to it, and challenge it with counter examples.

(And indeed, you’ll see that specific examples turn up here in this comment thread as arguments against it; notably not picked up to be addressed by the OP in their hacker news feedback section)

noodletheworld··on Do the simplest thing that could possibly work
Yes, but this is meaningless advice.

The best solution is the simplest.

The quickest? No the simplest; sometimes thats longer.

So definitely not a complex solution? No, sometimes complexity is required, its the simplest solution possible given your constraints.

Soo… basically, the advice is “pick the right solution”.

Sometimes that will be quick. Sometimes slow. Sometimes complex. Sometimes config, Sometimes distributed.

It depends.

But the correct solution will be the simplest one.

Its just: “solve your problems using good solutions not bad ones”

…and that indeed both good, and totally useless advice.

← PreviousPage 5 of 8Next →