HNHacker News
TopNewBestAskShowJobs

MattCruikshank

332 karma · joined February 23, 2010

submissionscomments
MattCruikshank··on Why I'm still bearish on LLMs after Navier-Stokes
> The fact that the human would have a much harder time writing a useful program is irrelevant.

Why?

There's a box.

You give it a problem, and it comes up with a solution.

Why does it matter to you if the box is strictly a LLM, or if the LLM can write code that it executes?

Even neater if the box is self-contained with a local model. You provide electricity, and it comes up with solutions. Why does it matter if it can do chess "in its head", or if it has to use scratch paper?

MattCruikshank··on Show HN: Capsule – Single-file web apps that save their data into SQLite
Neat!

Another way to achieve something like this is Cosmopolitan C Compiler, Actually Portable Executables. For example, Redbean. (Jart, all of your certs are bad! I can't open your websites any more!) http://justine.lol/

It's a binary that can run on Windows, Mac, Linux, and it is also a zip file. The application can read the zip file and on several systems (not Windows), it can self-modify the zip file. Including hosting SQLite inside the ZIP file.

MattCruikshank··on Why I'm still bearish on LLMs after Navier-Stokes
What happens when you ask those same frontier models to write a chess-playing program?

I feel like, this is a huge stumbling block that many people have. They'll give a model their data, and ask it questions. I vastly prefer letting the model understand the schema, and then writing functions or programs to answer those questions. I feel like I get way, way better answers. I can have it write unit tests for those functions. I can fuzz test those functions. I can look for data that doesn't fit the schema. I can process new data way faster (and with fewer tokens). I can repeatably get the same answers from the same inputs. I can check the code into a git repo and track changes to it over time. I can share the code with other people. I can review the code. I can improve the speed of the code and get the same answers. I can review the error accumulation, and improve it. I can decide how to handle anomalies, and encode those answers.

It's really neat to see what a frontier model can do itself. No doubt.

But "play chess by hand" is a frankly awful metric. It's kind of like asking someone to take a cube root of some arbitrary decimal, in their head, with no scratch paper.

MattCruikshank··on An update on Wayback Machine access
My desired usage pattern stands... Someone who publishes content shouldn't be punished for everyone else wanting to access it, and shouldn't have to resort to product placement, advertising, sponsorship, or begging to fund it.

I don't know, maybe WebTorrent should have been the answer? For upcoming, viral content?

But for the deep archives, like the Wayback Machine? I feel like I'd happily pay for egress, and a bit to support them. If it was automatic and built in...

I wish Flattr or something like it had thrived...

MattCruikshank··on An update on Wayback Machine access
There was a feature on Amazon Web Services for a while, and I wish it was still there...

Downloader pays.

I make some content and upload it. When you want to download it, you pay Amazon the egress fees. And maybe I get to charge just a bit more, to help me with the Ingress, storage, content creation, etc.

I mean, I know that there's going to be problems with rate limiting, etc. And yes, we have those problems with LLM tokens today. But this just feels like such a useful thing that it baffles me that it doesn't exist already.

MattCruikshank··on Steam Frame starts at $1059
Standalone? No. Most PC VR headsets require a PC. The Steam Frame will let you play 2D games (and some VR games), with no phone or PC attached.
MattCruikshank··on MIT creates method to force AI to comply with safety rules
[Cackles in Jeff Goldblum.]
MattCruikshank··on Mark Cuban: Why US hospitals "don't know their costs"
Some practices are self-insured. Some practices have to pay the first million, up to five million, out of pocket.
MattCruikshank··on Mark Cuban: Why US hospitals "don't know their costs"
Every prospectus I've ever read, "Past performance is no guarantee of future results."
MattCruikshank··on Mark Cuban: Why US hospitals "don't know their costs"
Let's say every now and then, you need to do X.

That means you need to be prepared to do X.

And what if some of the components of X expire? That means you have to pay to keep them on hand.

And the distribution of how often you do X is absolutely not predictable. Sometimes it's months between them. Sometimes it's 10 in a day.

If you had to be prepared to serve 20 hamburgers, any given afternoon, with no warning, how much ground beef would you waste, over a year?

Counting how much ground beef you did use does actually provide some information. I'm not discounting that. But it absolutely does not tell the whole story.

MattCruikshank··on Mark Cuban: Why US hospitals "don't know their costs"
My insurance premiums go up on their own. They go up more when I file claims. I'm betting the same is true of hospitals.
MattCruikshank··on Mark Cuban: Why US hospitals "don't know their costs"
> they don’t know what a bill of materials is for a hip replacement. Rather than identifying the actual labor, supplies, implants, overhead and other expenses tied to an individual procedure...

How often is there a malpractice case for a hip replacement?

I'm willing to bet that the costs of a malpractice case can be one, two, three, or even more orders of magnitude higher than all of those other expenses. Dwarfing any of those enumerated costs. Even cases that they win.

Of course they're looking at the statistics rather than counting beans.

MattCruikshank··on Trade (and Tariffs)
Sorry, I didn't mean to imply you didn't know.

I meant, "Yes, you're so damned right! It's even in the dictionary! I wish people would educate themselves and not believe lies!"

MattCruikshank··on Trade (and Tariffs)
Merriam-Webster: "The meaning of TARIFF is a schedule of duties imposed by a government on imported or in some countries exported goods."

Apparently the dictionary is "woke."

Wikipedia: "A tariff, or import tax, is a duty imposed by a national government, customs territory, or supranational union on imports of goods and is paid by the importer."

Oxford Economics: "Tariffs are taxes imposed by a government on goods and services imported from other countries."

MattCruikshank··on Trade (and Tariffs)
Yeah, I think you've got it. Agreeing with you and continuing my thought:

If I had to guess at the comic author's intention...

It's commentary that the logic is flawed. If this is why you're doing tariffs, you're not using them correctly.

Not that tariffs should never be used.

MattCruikshank··on Trade (and Tariffs)
How many 100% tariffs do you have on every good from an entire country?

A scalpel is one thing.

Dynamite is something else.

MattCruikshank··on Trade (and Tariffs)
It would certainly help if people wouldn't believe flat-out lies.

Like, "other countries pay the tariffs."

No. They don't.

How can we have nuanced conversation about the trade-offs, if the leader of one political party blatantly lies about a fundamental detail of how tariffs work?

600% reduction in the price of drugs?

We can't even start a discussion with people who believe this. At all. They reject any information, even their own knowledge of how numbers work.

MattCruikshank··on Tailcat – Like netcat, but over Tailscale’s data plane
The author is Brad Fitzpatrick.

He worked at Google for 12+ years. He created memcached, WebSub (PubSubHubbub), OpenID, and Perkeep (Camlistore). He's a late-stage co-founder of Tailscale.

If he's a junior engineer, then I have no idea what a senior engineer is.

MattCruikshank··on Tailcat – Like netcat, but over Tailscale’s data plane
...this is a github repo. Pointing to an open source project. That is not forced to use any vendor-specific systems to function.
MattCruikshank··on Exact, parallel 2D Delaunay triangulation for int32 coordinates
I upvoted, I favorited, I starred the repo, and I even used a smiley.

What has OP done for me lately? :)

MattCruikshank··on Exact, parallel 2D Delaunay triangulation for int32 coordinates
Neat, now do a 3D Delaunay tetrahedrization! :)
MattCruikshank··on Cloudflare OS: an open platform for agents, apps, and work
Great! I'm really excited.

So, I want to make an RSS feed Gadget. And you will run an RSS Aggregator Gadget, and then some Presentation Gadget. Do I have that roughly right?

How does my Gadget talk to yours? Cloudflare Tunnels for CGNAT, NAT traversal? CapnProto for the schema? Fire and forget? Online only? Queuing? Store and forward?

How do I keep track of my Contacts? Who is allowed to read my feed? Are controls built in?

So so so many questions. Do you have office hours? :D

MattCruikshank··on Changes at Google DeepMind: Demis Hassabis from CEO to Chair, Jeff Dean departs
Did Jeff and Sanjay pair write their resignation letter? Wow.
MattCruikshank··on Fields Medals 2026
There are actually championships. People do refer to different bots at being at the Master level, Grandmaster level, etc. In Chess, in Go, etc.

They might not be officials, they not might represent the official organizations, but those things do happen.

MattCruikshank··on Fields Medals 2026
We know which bots are the best at Chess. You'd care which AI is the most accurate at diagnosing your medical condition. It's not a bad thing to keep track of which automated systems are the best at certain tasks.
MattCruikshank··on First atmosphere found on Earth-like planet in habitable zone of distant star
Sure, but keep in mind that technically New Jersey is "habitable," so don't get too excited.
MattCruikshank··on Jurassic Park computers in excruciating detail
I feel like there should be an online museum dedicated to reproducing the graphics in movies, as faithfully as possible.

Especially awesome if film-makers started DONATING their video assets to the museum.

MattCruikshank··on How We Made IPFS Content Publishing 10x Faster
It doesn't seem like it's popular to put old game ROMs on IPFS...? And that surprises me...
MattCruikshank··on CSSQuake
Don't worry, OP still can't center a div.
MattCruikshank··on Show HN: FablePool – pool money behind a prompt, and Fable builds it in public
Wouldn't it be better to just have an open source project, where everyone picks some tasks for their "spare" tokens to implement?
← PreviousPage 2 of 4Next →