misja111

To me, the real question after reading this, is: Is your new implementation of Azure’s RSL now being used?

If it is, and it works well, then to me this is far more meaningful than the fact that AI wrote 130K lines of code.

It's not about traceability, it's about not having to use the dollar as currency.

exactly! This should have been part of the prompt. If you choose not to do this then you shouldn't be surprised about the high token usage.

There are several cases where this is not possible or desirable:

- you are using AI as an E2E testing tool and it's a requirement to not just test the API but also the workings of the UI

- you are using some third party tool and want to automate its usage

> Every function is a specification that the compiler can verify against its implementation.

This has been tried so many times already. It works nice for functions that only do some arithmetic. But in any real life system that pushes data around over the network or to databases, most things will happen inside effects which leaves the compiler clueless as to whether the function implementation does what it's supposed to do or not.

Don't get me wrong, I'm a big fan of using the compiler to improve productivity and I also believe strong typing leverages LLM power. But this kind of function specification is a dead end IMO.

The root cause of some of the bugs seems to be the opaque nature of some of the Unix API. E.g.

> The trap is that get_user_by_name ends up loading shared libraries from the new root filesystem to resolve the username. An attacker who can plant a file in the chroot gets to run code as uid 0.

To me such a get_user_by_name function is like a booby trap, an accident that is waiting to happen. You need to have user data, you have this get_user_by_name function, and then it goes and starts loading shared libraries. This smells like mixing of concerns to me. I'd say, either split getting the user data and loading any shared libraries in two separate functions, or somehow make it clear in the function name what it is doing.

I have been doing this for years already after finding out by myself that it worked. Staring at anything works, even staring at your screen as long as you make sure you focus out.

> How do you think engineers in the second half got there? By writing tons and tons of code to "build those reps" and gain that experience.

Well this is true, but that doesn't mean that there isn't any other way to acquire this knowledge. Until now, this way of gaining deeper understanding was simply the most practical one, since you needed to write lots of code when starting out as a software engineer.

But it's just as well possible to gain knowledge about useful abstractions and clean code by using AI to do the work. You'll find out after a while which codebases get you stuck and which code abstractions leverage your AI because it needs fewer tokens to read and extend your codebase.

Is 4.6 without adaptive thinking better than 4.5? Honest question. I switched back to 4.5 because 4.6 seemed mostly to take longer and consume more tokens, without noticeable improvement in the end result.

Well the fix is simple, just use 4.6 or even 4.5

I'm actually seeing a similar thing when comparing 4.6 and 4.5. It burns a lot more tokens, does show more how it is thinking along the way, but I don't see a strong difference in the end result. Occasionally 4.6 even seems to get stuck in its 'processing' phase, while 4.5 doesn't on the same task.

I disagree. Much of what makes software complex for us, makes it complex for LLM just as well. E.g:

- a very large codebase

- a codebase which is not modularized into cohesive parts

- niche languages or frameworks

- overly 'clever' code

I'm playing backgammon. Not just online, but live tournaments as well.

What I like about it: it's one of those games that are easy to learn but difficult to master. Modern analyzing tools can detect your errors and weaknesses, providing you with eternal possibilities to improve.

But also, I like the excitement of the live tournaments, which like poker, have money prizes and an entry fee. They are all over the world and I especially like visiting tournaments in places which I otherwise wouldn't visit. Plus after a while you'll make friends in the tournament circuit, so it becomes a social thing as well.

Where did you get those points from? Do you have a source? The 10 points I've read in the media are different, e.g. https://www.thenationalnews.com/news/us/2026/04/08/what-is-i...

I was replying to OP who sketched the scenario

> Worst outcome is the US attacks Cuba ..

As you probably know POTUS was announcing already that Cuba would be next.

> If this happens and Cuba decides to launch drones/missiles against the US homeland, it's not an exaggeration to say that Cuba is flattened and invaded that same afternoon.

Yes that would be a typical US solution. Let's liberate the Cuban people! By flattening them.

Can anybody explain how these plug-in solar panels work? I am suprised that it's possible to just plug them in to your wall socket.

For instance, isn't it complicated to have their output be in perfect sync with the frequency that comes in via the electricity net? Because to me it seems that if they won't, you will have lower benefits or even a net minus after plugging it in.

It depends. If all I want is some prototype or pet code project, my LLM can write most by itself. The speedup could be 10 times or more. However, if I'd let a LLM write code for my work, I'd have to very thoroughly review it and most likely ask it to rewrite it several times. Each time this would require a new review of course. There would still be a speed up but I guess at most somewhere around 25%.

In practice I try to combine the best of both worlds. I write some code by myself and rely on my LLM for parts that are not too big and where I expect it to do a pretty good job.

I can't imagine he's building anything serious. How can you claim otherwise that your agents were deploying code that you couldn't verify. Imagine doing that in any serious business ..

Speak for yourself, I don't ship any code that I don't fully understand. Yes that requires less autonomous AI and less frequent merging. But I don't even want to think about the disasters that could happen if you really get into the habit of shipping code you can't verify or understand.

> At some point you're not reviewing diffs at all, just watching deploys and hoping something doesn't break.

Good luck doing that in any company that does something meaningful. I can't believe anybody can seriously be ok with such a workflow, except maybe for your little pet project at home.

Most likely they will put the blame on the 'disloyal' supreme court and not on Trump.

So effectively US citizens have been paying an extra tax, which money flowed to certain companies. I can't wait to hear the justifications that will follow from the Trump government.

This is not entirely true. In an environment driven by business stakeholders, the engineer who ships features quickly, and that break rarely in production, will be greatly appreciated. The engineer who takes weeks to over-engineer a simple feature, which then runs into unexpected side issues in production, much less so.

The environment where the over-engineer tends to be promoted is one where the engineering department is (too) far separated from where the end users are. Think of very large organizations with walled departments, or organizations where there simply is not enough to do so engineers start to build stuff to fight non existing issues.

And the alternative is ... Russia? A corrupt dictatorship whose economy is kept alive with government war spending?

I guess it's the same principle, an excess of adenosine in your brain because of the mental strain you put on yourself during the workout.

In my experience, it's the workout itself that ruins sleep when it's in the evening. My theory is that it's because of the adrenaline generated by muscle strain.

I have noticed that the reverse is also true: a heavy workout makes it more difficult to think hard afterwards.

> People seem to think only money has value.

Your either don't understand or don't want to understand what people are commenting about here. Of course nobody thinks that only money has value. If only money had value, why would anybody exchange money for, say, a bread?

What many people are wondering about, is whether the value of the money paid by tax payers to artists, equals the value of what they give to the tax payers in return. Because if it would be equal, then one might wonder why they apparently are not able to sell their art for the same amount of money.

Yeah but then this was called a subsidy so it would never have made the HN frontpage.