111–120 of 334 posts
I’ve observed exactly these patterns with Opus and Fable as well - for example, forgetting that they can edit files and instead use python scripts as a patching tool…
The harness instructs them to behave this way. Also this approach saves tokens. The scripts allow to edit files in bulk, and most of the session cost is in cache reads (e.g. for 300K context each command costs the same as 30K input tokens).
51 comments so far, the vast majority panning Astra's coding abilities. An uninformed reader may come away with the impression that this isn't an absolutely revolutionary technology that with coding abilities many of us thought were not even going to be possible with language models as recently as a year ago. Yeah, it's not perfect, but it's really good and extrapolating this rate of improvement for 6 months is rathe…
I’ve observed exactly these patterns with Opus and Fable as well - for example, forgetting that they can edit files and instead use python scripts as a patching tool…
Why would you use a constrained edit tool when you are also allowed to use the complete power of python?
Earlier quoted context omitted.
Why would you use a constrained edit tool when you are also allowed to use the complete power of python?
Simple is better than complex Complex is better than complicated Or something, I don't remember...
I’ve observed exactly these patterns with Opus and Fable as well - for example, forgetting that they can edit files and instead use python scripts as a patching tool…
Why would you use a constrained edit tool when you are also allowed to use the complete power of python?
Ironically I burned out Fable usage early this week because of Astra using it to run inane full codebase reviews over one line changes, so I have been using Astra extensively. We need a word for “potentially highly capable, but in reality an idiot savant” to describe certain models. No, I don’t need you to write a tmux emulator in bash to test your changes bro, just ask me to run the command.
Earlier quoted context omitted.
But doesn't this reduce the required amount of farmland?
There is no “required” amount. More gets produced using the same area, using more people, but keeping these people in poverty because productivity per capita doesn’t increase. Instead the gains from the increased volume of production get captured by an elite. See https://link.springer.com/article/10.1186/s41257-019-0021-y .
Early lesson I learned from AI engineering was - there is no substitute to giving a groomed epic to an agent. Instead of simply saying 'implement themes in my product' you need to be specific, in fact more specific than usual. You need to say exactly what is in scope and what's not, even down to a buttons, events and layouts. You can groom the epic with the help of AI, but final review must be done by someone who can…
> Instead of simply saying 'implement themes in my product' you need to be specific, in fact more specific than usual. Around February you could get away with very vague prompts to Claude. I feel like models have regressed since
I sincerely don’t understand what the people who say they no longer read any code are doing, because it must be somewhat trivial to not run headlong into these issues that stack up time after time - then people say to just prompt better and it doesn’t have that problem for them, but I look at those same people’s code and it’s horrific, and then I find they haven’t made it far past a proof of concept phase. I watch entire teams slow down to a crawl and not be able to handle changes, or production incidents. This seems common among many people I talk to.
I personally think that the boosters need to put up or shut up - the promises are way over the skis. Every single person I’ve seen being a strong proponent of these techniques both has nearly unlimited tokens to spend and also seems to be in the business of selling a solution. I can’t find many not-currently-marketing-something engineers succeeding using these techniques in production systems unless they’re quite simple, or doing a very specific task from a more mature codebase.