Comment by champagnepapi
14 hours ago
agreed. All of these are trying to get to something that can't really every be achieved with LLMs with is determinism. Folks are trying to constrain the models to behave in a certain way with all of these tools, but there's far too many edge cases for them to be reliable. Doesn't mean they can't add some value, but it seems very limited. Hoping it's only a matter of time before we go back to engineering and step back from "vibes".
I felt that way initially. It is also a headache when you invest a lot in that and need to continually test ripping that stuff out as new models come out. Or in the case of opus 5, Anthropic says ditch it entirely and trust it.
But there is another aspect which I do enjoy which is closer to the feeling of dialing in key bindings in vim or getting a really good rhythm going with your vscode extensions or zhs plugins. It is that level of "I want my system to do exactly this thing in exactly this way" customization that a lot of technical people crave.
And you can do it with harness and context engineering in many cases. In other cases it introduces friction because it will be like "cool, I will only output 15 words max unless told otherwise" and then in the next turn completely disregards it with an "oops, you did tell me to do that didn't you."
And that frustration compounds when older model versions may have done a better job of that but new models are like "thank you for your suggestion, your opinion, while appreciated, is irrelevant. Now let me get back to overspending on your token budget. "
We won't. AI engineering is here to stay whether people like it or not.
See what some guys like Linus Torvalds, or Eric S. Raymond are saying about. It's not so much about "vibes" but using the tool (yes the AI tool) in a certain way that can propel yourself towards your goal at unprecedented speeds.
> It's not so much about "vibes" but using the tool (yes the AI tool) in a certain way that can propel yourself towards your goal at unprecedented speeds.
I think most would agree with that, unfortunately, this is not how LLMs or agentic flows are being marketed, nor how firms are encouraging their users to use them. It's being sold in a manner completely different from its capabilities.
I've maintained this for a long time but if AI was being sold as a way to achieve superhuman levels of productivity and to help you with certain goals or tasks then people would be far less opposed to its adoption. The social havoc it's wreaked as a result of Altman et al.'s bluster about it being a fully ready, human-level replacement for humans has done its reputational damage and it will take years for that to recover, especially given that they don't seem to care (yet).
So AI is mostly a thin glue between deterministic processes. Doesn't change the fact that that is enough to achieve an extremely large amount of tasks.