21–30 of 218 posts
[flagged]
Imagine how useful it would be we could just add a button show our approval or disapproval of a piece of content without having to type true or false in the comment section. Let’s call it upvote or downvote button. /s
On the other hand, I don't know what this mythical downvote button for stories is you describe. I've certainly never seen it.
Would be nice if HN actually had that.
Since agents are good only at greenfield projects, the logical conclusion is that existing codebases have to be prepared such that new features are (opinionated) greenfield projects - let all the wiring dangle out of the wall so the intern just has to plug in the appliance. All the rest has to be done by humans, or the intern will rip open the wall to hang a picture.
Sure you can't point it to a Jira ticket and get a PR but you certainly can use it as a pair programmer. I wouldn't say it is much faster than working alone but I end up writing more tests and arguing with it over error handling means I do a better job in the end.
Since agents are good only at greenfield projects, the logical conclusion is that existing codebases have to be prepared such that new features are (opinionated) greenfield projects - let all the wiring dangle out of the wall so the intern just has to plug in the appliance. All the rest has to be done by humans, or the intern will rip open the wall to hang a picture.
People should be worried because right now AI is on an exponential growth trajectory and no-one knows when it will level off into an s-curve. AI is starting to get close to good enough. If it becomes twice as good in seven months then what?
AI raises everything - the ceiling is just being more productive. Productivity comes from adequacy and potency of tools. We got a hell of a strong tool in our hands, therefore, the more adequate the usage, the higher the leverage.
People should be worried because right now AI is on an exponential growth trajectory and no-one knows when it will level off into an s-curve. AI is starting to get close to good enough. If it becomes twice as good in seven months then what?
GPT-1 June 2018
GPT-2 February 2019
GPT-3 November 2021
GPT-4 March 2023
Claude tells me this is the rough improvement of each:
GPT-1 to 2: 5-10x
GPT-2 to 3: 10-20x
GPT 3 to 4: 2-4x
Now it's been 2.5 years since 4.
Are you expecting 5 to be 2-4x better, or 10-20x better?
Because it can't actually model these complex problems, it really requires awareness from the user regarding what questions should and shouldn't be asked. An LLM can probably tell you how a knight moves, or how to respond to the London System. It probably can't play a full game of chess with you, and will virtually never be able to advise you on the best move given the state of the board. It probably can give you information about big companies that are well-covered in its training data. It probably can't give you good information about most sub-$1b public companies. But, if you ask, it will give a confident answer.
They're a minefield for most people and use cases, because people aren't aware of how wrong they can be, and the errors take effort and knowledge to notice. It's like walking on a glacier and hoping your next step doesn't plunge through the snow and into a deep, hidden crevasse.
it feels like when you need to paint walls in your house. If you've never done it before you'll probably reach for tape to make sure you don't ruin the ceiling and floors. the tape is a tool for amateur wall painters to get decent results somewhat efficiently compared to if they didn't. If your an actual good wall painter, tape only slows you down. You'll go faster without the "help".
I recall he mentions in this video that the new advice they are giving to founders is to throw away prototypes when they pivot instead of building onto a core foundation. This is because of the effects described in the article.
He also gives some provisional numbers (see the section "Rapid Prototyping and Engineering" and slides ~10:30) where he suggests prototype development sees a 10x boost compared to a 30-50% improvement for existing production codebases.
This feels vaguely analogous to the switch from "pets" to "livestock" when the industry switched from VMs to containers. Except, the new view is that your codebase is more like livestock and less like a pet. If true (and no doubt this will be a contentious topic to programmers who are excellent "pet" owners) then there may be some advantage in this new coding agent world to getting in on the ground floor and adopting practices that make LLMs productive.
People should be worried because right now AI is on an exponential growth trajectory and no-one knows when it will level off into an s-curve. AI is starting to get close to good enough. If it becomes twice as good in seven months then what?