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.
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."
Don’t forget the requirement of not dropping frames under load. The browser engine might have assumed that requirement throughout the entire code base.
With agentic loops, you specify what you want and it continues to do stuff until ‘it works’. Then publish. Its takes less time and attention. So projects are less thought out and less tested as well.
In the end, I think it’s not about how a project was created. But how much passion and dedication went into it. It’s just that the bar got lowered.
Every market on some level can be analogized to a common and simple market.
One of the common examples in management books is the signage industry. You can have custom logos custom molded, extruded, embossed, carved, or at least printed onto a large, professional-looking billboard or marquee size sign. You can have a video billboard. You can have a vacuum formed plastic sign rotating on top of a pole. At the end of the day, though, your barrier to entry is a teenager with a piece of posterboard and some felt-tipped markers.
What has happened is that as the coding part has become easier, the barrier to entry has lowered. There are still parts of the market for the bespoke code running in as little memory and as few CPU cycles as possible, with the QA needed for life-critical reliability. There’s business-critical code. There’s code reliable enough for amusement. But the bottom of the market keeps moving lower. As that happens, people with less skill and less dedication can make something temporary or utilitarian, but it’s not going to compete where people have the budget to do it the higher-quality way.
How much an LLM or any other sort of agent helps at the higher ends of the market is the only open question. The bottom of the market will almost certainly be coded with very little skilled human input.
This direction could be an interesting AI benchmark. All kinds of different humans use LLMs for their job, whether allowed or not. Including diplomats, defence personnel, lawyers etc etc. Within the benchmark you could play both sides and reward when both sides reach some kind of mutually beneficial game theory scenario where both parties win.
reply