Thanks for this. The guy really wants to pin me on the 10x thing coming from him but I keep saying it's not and he keeps ignoring me. The claims of his article are extremely plain and clear: AI-loving engineers are going "rocket fuel" fast, AI skeptical engineers are crazy (literally the title!) and are sitting still.
My post is about how those types of claims are unfounded and make people feel anxious unnecessarily. He just doesn't want to confront that he wrote an article that directly says these words and that those words have an effect. He wants to use strong language without any consequences. So he's trying to nitpick the things I say and ignore my requests for further information. It's kinda sad to watch, honestly.
I'm happy to hear that! A lot of people posting their hot takes here about how AI is actually great or actually awful, but I was hoping to have more conversations like this in the comments. I'm glad I can help people feel better.
What did you set the context window to? That's been my main issue with models on my macbook, you have to set the context window so short that they are way less useful than the hosted models. Is there something I'm misisng there?
I've done a few of these types of hands off and go to a meeting style interactions. It has worked a few times, but I tend to just find that they over do it or cause issues. Like you ask them to fix an error and they add a try catch, swallow the error, and call it a day. Or the PR has 1000 line changes when it should have two.
Either way, I'm happy that you are getting so much out of the tools. Perhaps I need to prompt harder, or the codebase I work on has just deviated too much from the stuff the LLMs like and simply isn't a good candidate. Either way, appreciate talking to you!
If you really need some, there are some links in another comment. Another one that was made me really wonder if I was missing the bus and makes 10x claims repeatedly is this YC podcast episode[1]. But again, I'm not trying to write a point by point counter of a specific article or video but a general narrative. If you want that for your article, Ludicity does a better job eviscerating your post than I ever could: https://ludic.mataroa.blog/blog/contra-ptaceks-terrible-arti...
I'm trying to write a piece to comfort those that feel anxious about the wave of articles telling them they aren't good enough, that they are "standing still", as you say in your article. That they are crazy. Your article may not say the word 10x, but it makes something extremely clear: you believe some developers are sitting still and others are sipping rocket fuel. You believe AI skeptics are crazy. Thus, your article is extremely natural to cite when talking about the origin of this post.
You can keep being mad at me for not providing a detailed target list, I said several times that that's not what the point of this is. You can keep refusing to actually elaborate on how you use AI day to day and solve its problems. That's fine. I don't care. I care a lot more to talk about the people who are actually engaging with me (such as your friend) and helping me to understand what they are doing. Right now, if you're going to keep not actually contributing to the conversation, you're just kinda being a salty guy with an almost unfathomable 408,000 karma going through every HN thread every single day and making hot takes.
Has happened to me before. It seems they change anything that has a negative connotation to try to take something more positive out of it. I don't love that they do that without asking or confirming with the author. But this title is also fine with me. I actually thought about naming it "Curing your AI 10x Imposter Syndrome", but it felt like a stretch that someone would understand what the content would be about.
What I'm saying is that the model will get into one of these loops where it needs to be killed, and I'll look at some of the intermediate states and the reasons for failure and they are because it hallucinated things, ran tests, got an error. Does that make sense?
Deleting and re-prompting is fine. I do that too. But even one cycle of that often means the whole prompting exercise takes me longer than if I just wrote the code myself.
I think I may have worded this poorly. I mean the total amount of code review time that goes into 3 months of work (likely on hundreds of PRs) can't be compressed into 1.5 weeks at the same portion of time being allocated to code review. Each code review has a "floor" time, a minimum amount of time loss due to context switching, reading, writing, etc.
> I mentioned in another comment the major flaw in your productivity calculation, is that you aren’t accounting for the work that wouldn’t have gotten done otherwise. That’s where my improvements are almost universally coming from. I can improve the codebase in ways that weren’t justifiable before in places that do not suffer from the coordination costs you rightly point out.
I'm a bit confused by this. There is work that apparently is unlocking big productivity boosts but was somehow not justified before? Are you referring to places like my ESLint rule example, where eliminating the startup costs of learning how to write one allows you to do things you wouldn't have previously bothered with? If so, I feel like I covered this pretty well in the article and we probably largely agree on the value that productivity boost. My point is still stands that that doesn't scale. If this is not what you mean, feel free to correct me.
Appreciate your thoughts on hallucinations. My guess is the difference between what we're experiencing is that in your code hallucinations are still happening but getting corrected after tests are run, whereas my agents typically get stuck in these write-and-test loops and can't figure out how to solve the problem, or it "solves" it by deleting the tests or something like that. I've seen videos and viewed open source AI PRs which end up in similar loops as to what I've experienced, so I think what I see is common.
Perhaps that's an indication of that we're trying to solve different problems with agents, or using different languages/libraries, and that explains the divergence of experiences. Either way, I still contend that this kind of productivity boost is likely going to be hard to scale and will get tougher to realize as time goes on. If you keep seeing it, I'd really love to hear more about your methods to see what I'm missing. One thing that has been frustrating me is that people rarely share their workflows after makign big claims. This is unlike previous hype cycles where people would share descriptions of exactly what they did ("we rewrote in Rust, here's how we did it", etc.) Feel free to email me at the address in my about page[1] or send me a request on LinkedIn or whatever. I'm being 100% genuine that I'd love to learn from you!
I'm happy to hear that! I hope you felt seen by this line from the article:
> Oh, and this exact argument works in reverse. If you feel good doing AI coding, just do it. If you feel so excited that you code more than ever before, that's awesome. I want everyone to feel that way, regardless of how they get there.
I mean throughput, not latency. As in if you ship 10 meaningful changes in a month before you now ship 100.
My point around waiting for things like code review is that it creates a natural time floor, the context switching takes time and slows down other work. If you have 10x as much stuff to get reviewed, all the time loss to context switching is multiplied by 10x.
With terraform, using a property or a resource that doesn't exist is effectively the same as an API call that does not exist. It's almost exactly the same really, because under the hood terraform will try to make a gcloud/aws API call with your param and it will not work because it doesn't exist. You are making a distinction without a difference. Just because it can be caught at runtime doesn't make it insignificant.
Anyway, I still see hallucinations in all languages, even javascript, attempting to use libraries or APIs that do not exist. Could you elaborate on how you have solved this problem?
> Wait, now you're saying I set the 10x bar? No, I did not.
I distinctly did not say that. I said your article was one of the ones that made me feel anxious. And it's one of the ones that spurred me to write this article. I demonstrated how your language implies a massive productivity boost from AI. Does it not? Is this not the entire point of what you wrote? That engineers who aren't using AI are crazy (literally the title) because they are missing out on all this "rocket fuel" productivity? The difference between rocket fuel and standing still has to be a pretty big improvement.
The points I make here still apply, there is not some secret well of super-productivity sitting out in the open that luddites are just too grumpy to pick up and use. Those who feel they have gotten massive productivity boosts are being tricked by occasional, rare boosts in productivity.
You said you solved hallucinations, could you share some of how you did that?
Perhaps that's my fault for making the title almost clickbaity. My goal was to get people who felt anxious about AI turning them into dinosaurs not feel like they are missing some secret sauce, so hopefully the reach this is getting contributes that.
Again, appreciate your thoughts, I have a huge amount of respect for your work. I hope you have a good one!
Perhaps I was not clear here. My point isn't to say that one PR gets merged in 3 months. My point is to say that, lets say, 15 PRs from one dev get merged per quarter in the old days, for a 10x productivity boost that means that roughly 15 PRs get merged per 7 business days now. My point is simply that the amount of time that goes into the basic lag cycle involved in code review can't be compressed to 7 days.
My goal here was not to publicly call out any specific individual or article. I don't want to make enemies and I don't want to be cast as dunking on someone. I get that that opens me up to criticism that I'm fighting a strawman, I accept that.
Your article does not specifically say 10x, but it does say this:
> Kids today don’t just use agents; they use asynchronous agents. They wake up, free-associate 13 different things for their LLMs to work on, make coffee, fill out a TPS report, drive to the Mars Cheese Castle, and then check their notifications. They’ve got 13 PRs to review. Three get tossed and re-prompted. Five of them get the same feedback a junior dev gets. And five get merged.
> “I’m sipping rocket fuel right now,” a friend tells me. “The folks on my team who aren’t embracing AI? It’s like they’re standing still.” He’s not bullshitting me. He doesn’t work in SFBA. He’s got no reason to lie.
That's not quantifying it specifically enough to say "10x", but it is saying no uncertain terms that AI engineers are moving fast and everyone else is standing still by comparison. Your article was indeed one of the ones I specifically wanted to respond to as the language directly contributed to the anxiety I described here. It made me worry that maybe I was standing still. To me, the engineer you described as sipping rocket fuel is an example both of the "degrees of separation" concept (it confuses me you are pointing to a third party and saying they are trustworthy, why not simply describe your workflow?), and the idea that a quick burst of productivity can feel huge but it just doesn't scale in my experience.
Again, can you tell me about what you've done to no longer have any hallucinations? I'm fully open to learning here. As I stated in the article, I did my best to give full AI agent coding a try, I'm open to being proven wrong and adjusting my approach.
My post is about how those types of claims are unfounded and make people feel anxious unnecessarily. He just doesn't want to confront that he wrote an article that directly says these words and that those words have an effect. He wants to use strong language without any consequences. So he's trying to nitpick the things I say and ignore my requests for further information. It's kinda sad to watch, honestly.