agentultra

Hundred percent. All about trade-offs.

Although proof techniques such as proof repair have come a long way, it’s still impractical for a lot of scenarios.

TLA+ is great for systems design and such. Quick check style tests are awesome and a very low bar to clear from unit tests.

Are they slow and brittle?

I like having both. Unit tests are a decent indicator for local development. Fast, quick to iterate on. Integration tests are slow as molasses and I can’t iterate with them when it takes 20 minutes to setup the suite and run everything. Too slow. But still useful as you say.

Djikstra seemed like he was mostly against testing. But only because he was for proofs. A unit test is a single example. The real way to demonstrate the absence of errors is to prove they aren’t there (vis a vis axioms and assumptions).

But most developers don’t have the mathematical sophistication nor the time.

It’s not that unit testing is useless. Just good to know what their limitations are and to plan your testing strategy accordingly.

I think the harnesses might get better. And the alignment and pre training. But I don’t think the LLMs will get much better… I don’t have any sources for that though. Just napkin math.

At the end of the day, even if it gets to 99.9999% reliably generate what an experienced programmer would expect… you still need to be an experienced programmer to know what to want and how to specify it.

I think the experience, institutional knowledge, and process knowledge are never going to be replaceable.

You’ll still need to learn what a cache miss is and how the heap works and when to use skip lists and all that. Otherwise you will just generate slop. An AI system is not able to replace a human.

“I built a thing with AI and I don’t understand it. I want to make changes and fix things and have no ability to theorize why it fails or how to fix it.”

Oh my. See, you have to be able to program it yourself before you can build it with an LLM. Otherwise you have no way of judging the output. AI isn’t going to make you a programmer.

Learning to program is.

Interesting article. My advice is to do it the old fashioned, hard way. There’s no royal road to knowledge, skill, and learning.

Might be because most hit their maximum growth but need to keep growing indefinitely or risk becoming a “mature” company?

I think we’re more likely to die of starvation from economic collapse, heat related stress, and complications from Long COVID than an algorithm waking up and destroying us.

Unfortunately our list of potential extinction events are far more banal than these self-aggrandizing prophesies from the oligarch class.

I’m the opposite. I don’t believe there is a royal road to understanding anything. For me, the process of programming involves frustration. That is usually when I find my greatest insights.

Syntax isn’t a big deal. Names either. You can look them up. Remember them. Language gotchas are annoying and sometimes problematic.

To me, our job is understanding problems. And for me, understanding the problem involves wrestling with the code. I learn much from modelling problems in code, building theories, testing them.

Once an LLM system has generated some code I haven’t learned anything. Even when I read through the solution. It doesn't require the same activation of my brain. There’s nothing quite like working through the problem yourself.

LLMs definitely feel like they are draining my passion for computers. There were plenty of folks who checked out or were never truly passionate about programming. Now they’re louder than ever. “Nobody cares about code,” and, “optimizing is a waste of time.” Now we don’t even want to understand how it works, or whether it works at all. They repeat the lines their master have told them: get on board or get left behind.

I’m pretty sure I am risking getting, “left behind.” But I’m okay with that. The tech is truly the least interesting thing to me. If I don’t have a career in 10 years… oh well. I’ll still be programming.

The EPA hasn’t been able to regulate anything since it’s been gutted by the current administration. Of course it’s going to scrap rules. We’re not even allowed to measure the effects of climate change.

> In practice, when you reach for a database engine you're actually reaching for four basic features: unique constraints, transactions, indices, and history tables.

That might be a very specific assumption. What about serializability? Replication? Materialized views? Procedures? Locking? Access control?

It’s cool to experiment and try new approaches. Neat one here.

Could still end up moving to Postgres.

You can work around 12. with constraint satisfaction solvers.

After generating the level structure, emplace an entrance and exit such that they are maximally apart. And emplace a strong monster in one of the rooms around the exit. And emplace a health potion in one room before the strong monster. And emplace treasure in the exit room.

That sort of stuff and be specialized and coded towards your particular games structures fairly easily.

Scale is much harder though. In something like NMS it’d be intensive doing such a constraint solver on the whole galaxy. Might work in chunks or regions though.

No. Dear lord no.

One thing I am getting really tired of is the growing inability to distinguish legitimate sources. I don’t want to have to play, “can you tell the difference?” It’s not fun being had by a liar.

I want human written content or nothing at all. I care about the struggle. I like the spelling and grammar mistakes. I enjoy the story between the lines. I like the growth of the author and watching them and their work evolve.

Generated fiction is boring because it has none of that. There is no life in it. No author.

“A human wrote it,” is a light trick. Ok, who? Where are they from? If you have to lie to give answers in order to convince someone they like the story you’re not proving that people prefer AI stories in my estimation: you’re proving that the test is a convincing lie. And maybe that people are gullible.

We already know how to solve for climate change. All that is lacking is political will. Not AI.

Why not both?

> just about everything in modern life, from streaming Netflix to running a dishwasher, consumes water at levels that can be portrayed as wasteful by hair-shirt environmentalists.

Ad-hominems in an Economist article. This reads more like an opinion piece than reporting. There are plenty of documented problems with water usage of data centres. Some can use it efficiently but it costs more to do so and many (most?) do not.

We are also in a time when most people would prefer to use that water for drinking, washing, cleaning… basically anything except data centres.

Don’t think many people are going to read this and think, “Gosh, I was a fool!”

Big congratulations to the world leaders and policy makers who were at the signing of the Paris Accord. Went home. And did very little about it. Now we output more CO2 faster than we ever have in our entire history.

At least the economy is doing okay… oh wait.

Maybe the reason action hasn’t happened is because the solutions would drive down income inequality?

Was hoping my kids wouldn’t have to live with the worst of it but it looks like we failed at that.

It is a bit of a pedantic argument but I get upset when people misuse the term, abstraction, and can feel the impulse to write a blog post like this.

I think it’s important to make clear the RL part and the alignment and parameter tweaking that gets done on models and inference engines. It makes them more understandable as mechanisms and less like wish-washy super intelligences that make their own decisions.

When these systems win math Olympiads, it’s not terribly surprising or interesting to me. Of course they will: we trained models to play nearly optimal chess games and Go. You tweak the rewards and sigmoid and you start optimizing the function towards your goal. This is how learning systems of all stripes work.

It’s still next-token predicting at the end of the day. I don’t think it’s a reduction-ad-absurdum.

But a lot of people still call it, “intelligence,” and try to use language that obscures what is happening in terms of anthropomorphic behaviour and not machine ones. That really does influence how we use these tools and profits those who would use them on us.

> If many people hated their products, they wouldn't use them

This might be true in a true, free market without monopolistic collusion and the abandonment of antitrust regulation and enforcement in the US.

In many cases people don’t switch to something else because there isn’t an alternative. Or because they don’t know how to change the defaults that come installed on their computer. Or they get a big scary warning if they figure it out and try.

I would have a hard time believing anyone who said Google was competing fairly and not juicing their numbers with Gemini. Like with search and ads, they have a lot of vested interest in profits and little regard for much else. There’s no reason to. Almost all safeguards on corporate behaviour have been taken off in the last bunch of years.

Google jumped at renaming Lake Ontario.

Of course they’re going to shove AI mode as the default on search and claim every user loves it.

I wrote an interpreter in Zig not too long ago. I’d definitely recommend more folks try it out. It’s a straight-forward enough project to dip your toes in emulation and see if it’s your jam. And it’s not a big enough project that you’ll get overwhelmed before you finish.

Not that much of a difference for the average or lower classes of people that outnumber the rich by quite a lot. It would have a great and positive impact for them.

I don’t like LSPs. They’re slow and bloated. I’ve been using clangd but I think I’ll stop. It’s slow as molasses. It constantly tries to insert headers into source files that cause compilation issues. There are easier and faster ways to jump to definitions.

I don’t use LSPs with Haskell anymore. I work on multiple projects which use different versions of GHC and the base library which means having multiple LSPs installed for each one. Trying to get eMacs to reliably detect which project is using which version is not something I have been able to figure out. Plus it’s slow and uses way too much memory.

At current job I’m doing C# and man does the ecosystem there really push you to use an IDE. Most of my org uses Rider. I find it just as fascinating that people actually like using tools like it. Too bad it doesn’t have a decent text editor built in.

It was already difficult to maintain before these tools went mainstream. I’ve worked with many a senior developer who couldn’t write a hash function, didn’t understand memory allocation, and could go on all day about best practices and lint rules. They could make things that, “work,” but couldn’t tell you why.

And that was fine! It was a pain. But people need to learn. If you had experienced people around who did know those things then everyone would learn and improve. Most of the time.

Also, we were limited in how much code, and therefore how much slop, we could produce.

Now everyone has a firehose aimed at production. It’s hard to keep up.

In an ideal world where the market is perfect, maybe.

But in reality entrenched market players have access to political influence that lets them stay entrenched. They’ve spent a lot of money since the Industrial Revolution to make sure we need them.

It’s not a perfect free market. There’s no such thing. Politics has a huge influence in economics and vis versa. They’re intertwined.

There’s no such thing as destiny.

You could also walk out your front door and get hit be a meteor tomorrow.

Most 17 year olds I know don’t want anything to do with AI and see the entire industry as an existential threat.

Nothing wrong with learning the theory and understanding the papers. Getting to that point you’ll have to get your fundamentals down. Might be an interesting exercise.

But as a future? I guess we’ll see. I suspect the next financial apocalypse will determine if there is one. Another AI Winter that may outlast all others so far.

I’d pay for a search engine these days if it meant good results and no AI. Kagi almost fits the bill.

Removing paywalled links is a great feature that any future competitor should pick up!

128-bit integers aren’t part of the standard (yet)… but the point is right; platform and architecture matter. Many aspects of them are defined by the compiler implementation.

Also ABI compatibility isn’t part of the C specification. Most implementers use System V ABI compatibility guidelines. Many compilers can output code for different ABI’s calling conventions. There’s more than one! Which you use depends on how crufty the code is and on the platform you are using.

I think the big advantage of C like languages here is the plethora of implementation defined platforms. That’s a huge network effect. If you want to target the 6502? There’s a compiler for it. Some chip you’ve never heard of? Probably some fork of GCC that targets it. Want to call some library function in some foreign binary written in a completely unknown language? If you can finagle the bytes and reverse engineer the calling conventions you can do it with C.

I think it might be that C does leave so much out of the specification and up to the implementation and platform that makes it unique and useful at times.

Blacklisting is a shady practice, unfortunately. They generally work on ranges and you don’t get much of a say. Most blacklist maintainers have a way for you to report a false positive. Responsiveness varies. Most maintainers will drop your range off the blacklist after a fixed period.

Or you can pay to get off the list.

Not all email services use blacklists anyway. Bit of a racket.

You can mitigate against it by hosting on a dedicated IP.

But I understand the risk. It’s really annoying when I send someone an email and they call me some days later wondering why I hadn’t sent them an email. Failures are often silent on the sending side.

It’s not for everyone. There are risks.

It’s not that bad, but it does require some effort. I self-host. I spend far more time using and enjoying email than I do maintaining the infrastructure.

However you do have to live with the occasional blacklist when you host on a VPS like I do. Some idiot in your IP range may get blacklisted for spam and then you get caught in it. It’s generally temporary.

And there are some corporate policies that will flat out reject emails from you which is fun.

I’ve probably spent less than 10 hours over the last 5 or 6 years on maintenance.

It’s designed to “feel” that way. It’s a computer program, not a person. People made it.

Don’t get fooled into treating these systems like they’re people or intelligent collaborators.

At the best of times these chat/agent/loop systems are gambling machines. Very expensive and heavily subsidized machines. Don’t forget to keep building your own skills. You never know when the bubble is going to pop and you don’t want to be left unable to do you job just because some big tech corp goes under.