I think alignment is the missing part of this post.
Creating something visually interesting Invisible-Cities-ish is basically a task with a billion or more satisfactory outcomes. You don't have a precise view on what makes an invisible city a good one as long as it has all the fancy looking bells and whistles. This means the AI can generate a bunch of tokens which as long as they technically work (which it seems the max-thinking did not fully) produce a "good" result. This makes you think - wow AI is impressive. However if many things in the system really mattered, it might have been much less successful as the AI may have made poor assumptions. This was basically a task that given a large volume of tokens and technical competence it's fairly easy for the AI to do a good job at because we don't evaluate it with any depth/precision. I think the same is true for music, where there are basically an infinite number of combinations of sounds, beats, melodies, etc. which are pleasant to hear - and songs aren't mission critical - so alignment is not a big issue. Generative AI is good at these tasks.
I built and use https://smalldocs.org, which is a rich document format (mermaid diagrams, nice formatting, etc.) for agents. So I’ll be like “sdoc me the architectural ideas for this feature” and it helps.
I see, so about 900 symbols per 30 minutes. IEX puts out one file per trading day with every trade on IEX, so you get the last trade for about 8,5k US symbols in one download the next day ~12GB compressed though. Has Yahoo ever throttled you at that rate?
It means the exposure of being in HN front page usually causes a sudden spike of visits, and the increased traffic was too much for the server so the service is down for new visitors.
> it takes months, years even, to notice the effects of bad architecture or of unmaintainable code.
I think this is a bad take... if you are going that long without noticing, you are (hopefully) delivering end user value all that time. That is the main driver of code. You can normally dig/hack/rearchitect your way out of an ugly code situation. If you've been building value for the last year based on the hacky code, that's a win.
I have leaned heavily into it… and became good at “agentic thinking”, but now I’m going to reverse. I have become dumber, sloppier, lazier, more distracted. I’m less happy than before. It’s hard to escape the productivity addiction and expectations though.
I've seen this happen to multiple co-workers, in the span of months. Two were laid off so I don't know how it's going with them, and another has backed off but not fully abandoned AI code. I'm resisting it entirely because of these problems.
I’m very interested in building tools for coding agents (where I spend a lot of my time).
I’ve been building https://smalldocs.org, it’s a simply styled, but functionally deep, artifact layer for agents. It’s open source and free to use.
Because it can incorporate charts, diagrams, spreadsheets, etc. in one artifact, it’s good for creating (and optionally sharing) agent created analysis.
It has a local library for all your Markdown files, and a cloud library (my one paid feature) too. Both support tagging and rich search/filtering. I find it turns SmallDoc artifacts into little checkpoints in work I can easily circle back to.
Creating something visually interesting Invisible-Cities-ish is basically a task with a billion or more satisfactory outcomes. You don't have a precise view on what makes an invisible city a good one as long as it has all the fancy looking bells and whistles. This means the AI can generate a bunch of tokens which as long as they technically work (which it seems the max-thinking did not fully) produce a "good" result. This makes you think - wow AI is impressive. However if many things in the system really mattered, it might have been much less successful as the AI may have made poor assumptions. This was basically a task that given a large volume of tokens and technical competence it's fairly easy for the AI to do a good job at because we don't evaluate it with any depth/precision. I think the same is true for music, where there are basically an infinite number of combinations of sounds, beats, melodies, etc. which are pleasant to hear - and songs aren't mission critical - so alignment is not a big issue. Generative AI is good at these tasks.
reply