Imagine you are the top engineer of your company. Everybody wants your attention, many meetings, design sessions, and of-course code reviews.

With Claude Code, I use Gitlab for reviewing code. And then I let Claude pull the comments.

It looks like the new UI has a big focus on multiple agents. While it feels wrong, the more you split up your work into smaller merge requests, the easier it is to review the work.

Chat first is the way to go since you want the agent busy making its code better. Let it first make plans, come up with different ideas, then after coding let it make sure it fully tests that it works. I can keep an agent occupied for over a hour with e2e tests, and it’s only a couple hundred lines of code in the end.

Obviously hardware wise the real blocker is memory cost. But there is no reason why future devices couldn't bundle 256GB of mem by default.

> no reason why future devices couldn't bundle 256GB of mem by default

Cost is a pretty big reason.

There is also https://microvm-nix.github.io/microvm.nix/ if you want increased isolation.

I can recommend MicroVM.nix, since it allows for multiple VM runtimes like QEMU, Firecracker, etc.

There's also nixos-shell for ad-hoc virtual machines: https://github.com/mic92/nixos-shell

I have found that maximising AI coding is a skill on its own. There is a lot of context switching. There is making sure agents are running in loops. Keeping the quality high is also important, as they often take shortcuts. And finally you need an somewhat of an architectural vision to ensure agents don’t just work in a single file.

This is all very tiring and difficult. You can be significantly better than other people at this skill.

This is not an argument for its revolutionary utility. Balancing rocks on the beach is very tiring and difficult for some people, and you can be significantly better at it. Not really bringing anything to the immediate conversation with that insight.

There are also software model checkers that can model distributed processes. You have to simplify the state a bit, otherwise you get a state space explosion.

I tried it out myself, I let AI add action transitions through the code, like: // A -> B: some description. Then I validate via a test that every action transition defined in my model is also defined somewhere commented in code, and other way around that every comment exists in the model.

Finally, I let AI write model check queries on particular properties. If I notice a particular bug, then I ask AI to analyze the model and the model check queries on why it could happen, and ask to strengthen it.

It sounds like a lot of effort, but I got it working in a half hour.

I wonder if something like Gemini Veo (AI video generator) could re-make old movies. It might be hard to keep the consistency over the entire movie.

Why would you want this?

I found that it normally takes one prompt early-on to go from 'vibe-coded spaghetti' to something having a decent architecture.

I cap my effort at 2-3 prompts. One to investigate obvious mistakes with a top model, 1-2 to try to fix them.

One of the most reliable ways to induce psychosis is prolonged sleep deprivation. And chatbots never tell you to go to bed.

Hm. It shouldn’t be too hard to add something to models to make them do that, right? I guess for that they would need to know the user’s time zone?

Can one typically determine a user’s timezone in JavaScript without getting permissions? I feel like probably yes?

(I’m not imagining something that would strictly cut the user off, just something that would end messages with a suggestion to go to bed, and saying that it will be there in the morning.)

Chatbots already have memory, and mine already knows my schedule and location. It doesn't even need to say anything directly, maybe just shorter replies, less enthusiasm for opening new topics. Letting conversation wind down naturally. I also like the idea of continuing topics in the morning, so if you write down your thoughts/worries, it could say "don't worry about this, we can discuss this next morning".

I know a few people who work 3rd shift. That is people who good reason to be up all night in their local timezone. They all sleep during times when everyone else around them is awake. While this is a small minority, this is enough that your scheme will not work.

I actually was considering those people. That’s part of why I suggested it shouldn’t be a hard cut-off, but just adding to the end of the messages.

Of course, one could add some sort of daily schedule feature thing so that if one has a different sleep schedule, one can specify that, but that would be more work to implement.

It's funny that you frame it that way, because it's the mirror of (IMO) one of their best features. When using one to debug something, you can just stop responding for a bit and it doesn't get impatient like a person might.

I think you're totally right that that's a risk for some people, I just hadn't considered it because I view them in exactly the opposite light.

Claude will routinely tell me to get some sleep and cuddle with my dog. I may mention the time offhandedly or say I'm winding down, but at least it will include conversation stoppers and decrease engagement.

from my (limited) experience of ChatGPT versus Claude, i get the same. ChatGPT will always add another "prompt" sentence at the end like "Do you want me to X?" while Claude just answers what i ask.

looking at my history recently, Claude's most recent response is literally just "Exactly the right move honestly — that's the whole point."

It'll ask if you're eating properly too! It's like a virtual mom! :-P

There are (illegal) ways to delay trains as a person

Should be noted that this is just a meme, nothing with real money. Its a joke based on the constant delay of DB trains

Don’t forget the requirement of not dropping frames under load. The browser engine might have assumed that requirement throughout the entire code base.