At this point, all of the AI coding assistants are in the same neighborhood. Decent at "advanced autocomplete", OK at code generation sometimes, and most are somewhere in the process of incorporating code context mechanisms. But what's next? Agentic behavior? Something else? My pet prediction is that we will see the emergence of a new programming language that's designed for use with AI and can be translated to a variety of popular languages. (Or if we're cursed, just javascript )
Most productivity tools optimize for completeness: more activity, more metrics, more detail. But a useful update is not a transcript of everything someone did.
It should explain what changed, why it mattered, and what happens next. My coding agent is not able to do this that well because of the context gap
Every credit system I've used bills on the API call, not the outcome. So when a model returns something plausible and wrong, the user pays, then pays again for the version they actually wanted. You've priced your own failure rate and handed the bill to the person who noticed it.
The counter I keep hearing is that inference costs money either way. True, and beside the point. If a generation is unusable because we routed it to the wrong model, that's our decision, not their prompt.
Two things fall out of eating it yourself, both good. You have to define unusable narrowly enough that it can't be gamed, ours is a same-prompt regenerate inside a short window and nothing else. And you start caring a lot about routing, because a bad route now costs you directly instead of quietly costing someone else.
Curious who's actually doing this and where it broke for you. Most pricing pages I read still bill per attempt and call it usage.
One interesting thing I came across this week was that the CEO of Duolingo first declared intentions to use AI to replace contract workers in some positions. However, they later withdrew that comment, making it clear that AI will not replace its employees.
Ahh, this type of discrepancy appears to be happening more often, to be honest. The same thing happened to Klarna not long ago. That AI will take care of everything in one minute, and then, hold on: in reality, we still need human workers.
I've just made my free tier worse for a group of people who did nothing wrong, and I can't work out what I owe them.
Background, anonymised as best I can. Until this week you could use the core function of the thing I build without an account at all turn up, get a result, look at it. You only had to identify yourself if you wanted to keep the output. This week I put a free account in front of it. Same allowance, same features, no card, but you now sign up before you get anything.
The reasons were dull and real. I couldn't attribute anything to anyone. I couldn't tell a returning person from a new one, so I had no idea whether people were coming back. And an anonymous endpoint that costs me money on every call was an abuse problem I was going to have to solve eventually regardless.
What I didn't think through is what to say about it. Three things I'm stuck on:
Every two-sided product has this moment: someone lands on your page and has to figure out which side they re on before anything else makes sense. One side has capacity to offer, the other wants access to it.
I ve cycled through three approaches and none of them feel solved:
Split hero, two CTAs. Clean in a mockup. In practice people read both columns, compare them, and stall. The decision gets heavier because you ve made it look like a decision.
One CTA, branch after signup. Converts better at the top. But a chunk of people pick the wrong path and have to back out, which is worse than stalling.
I always aim to raise topics and questions relevant to startups/products and my personal endeavors that others might relate to.
The threads usually start with an intro to the topic, my experience, and, lastly, ask others to share their experiences. I try to structure these parts into clear, error-free sections so that they are easy to read. I have never used AI, for what it's worth.
