I'm not sure I like this form of content. It's hard to read and confusing on mobile for little gains. The article seemed interesting though.

Out of curiosity I asked Codex to build a version of this article that can be read/scrolled in a normal way while preserving the original graphics/text. Codex built it in about 10min with GPT-6.1 Sol High (consumed 8% of my 5h quota). It even thought of adding a dark/light mode switcher which is useful too. It still needs a few prompts of minor polishing, but already more readable to me.

Or you could just save all that time and effort and scroll through it like a reasonable person.

If you use Reader View in your browser, its much easier to read.

I personally hate all sites that hijack my scroll wheel for animation purposes.

On desktop it is very difficult to read.

I'm trying to fix the "agent said work was done, it was not" problem by defining work as runnable specifications in the form of a pytest suite.

Work is first defined in new or updated specifications, then the change gets made. You have to resist making natural language Todo lists and have the agent write runnable unit tests. My project is a CLI tool so it's fairly easy.

Verifying if it's done is a matter of running the specifications test suite.

In a totally not original way, I'm testing this workflow in my own agent orchestration tool. I know, there's just so many already. I'm building it for myself.

So far, the system is holding up but it's way too early to declare it a success.

You can check it out here:

https://github.com/egzo-ai/egzo/tree/main/specs

I think the same idea could be applied to other projects in different domains.

With this workflow I can read and update the specs, and run it against a built binary and be much more confident that the code works. Claude code has picked up the system without complaining for the most part.

Opus 5.5 in Claude code added a unit test checking DNS and internet access using example.com as the target on a project I'm building yesterday. It's an agent sandbox (I know, yet another), so the call was expected to fail, but still... It should have at least targeted a captive portal endpoint or a project owned domain.

I caught it in review but thousands of others won't.

That ship has sailed I would say.

If it breaks in those thousands of projects, that will be an important lesson to review your agents more carefully. So a net win?

More likely the agents will fix it as fast as they made it and people will continue not caring so much about reviewing what agents are doing for cases where they don't care so much (which is a lot of cases)

Coincidentally I mis-prompted claude code the other day while working on a toy project and failed to specify the project should be built on top of docker and not "like docker".

It went on to waste all my tokens creating a specialized docker clone. Cool I guess.

They will do these prompt just fine but the result will be a near identical copy of an open source version. And it won't tell you it cloned some existing engine, because it does not know, it just pulled it out from its model. Now you have an AI slopped 3d engine or DBMS no-one cares about that will just rot.

This is certainly true but I am also seeing some contrarian signals: people shaming you for doing stuff AI is faster at or having absolutely no shame or being proud of using AI for their work... To the point of not realizing how useless that actually makes them. And they get promoted.

Agreed. I carefully choose the software I use because I believe the author poured in some domain specific knowledge and made a tool that is novel and carefully thought through.

That does not mean a clever user cannot use an AI tool to help produce it, but so far most of it is slop. Some clever users can build some gems though.

It never does because however you frame it, AI is always the perfect scapegoat.

"Oh, I'm sorry, the bug was introduced by the AI and it made such a good case for it. Damn you claude, we'll do better next time. I'll add a code-review agent to find regressions."

this seems to be the true killer app of AI - accountability proxies. its interpersonal opium to have a third party that two ostensibly-in-conflict people can sink their negativity into.

its a major reason why military use of AI is so chilling - "look, I explicity ASKED the murderbot not to kill babies when I authorized the napalm strike on the maternity ward! BAD BOT"

Yup.

And it's also the kind of solution a misaligned agent would implement:

Make sure users are happy about their experience but also optimize resources.

The obvious solution is to route users based on feedback.

Yup. I remember my dismay when I started working with Linux on arm boards and realizing the absolute massive gap between the hardware vendor claims of "full linux support" and the reality.

Sometimes the SDK is a zip of the developer workspace in a pseudo working state with no clear records of all that's been patched.

Vendors providing binary only kernel and system images containing god knows what is not uncommon either.

I'm convinced now that arm hardware vendors are simply incapable of even understanding what proper software support is. I'm sure some of their devs do their best but management does not care. By the time the chip ships, efforts move to making the next thing so they never properly finish the software side.