As a research project, I built a needed tool with Claude Code. I thought it would be a disaster, but it wasn't. I have some complicated feelings about it.
26
Replies
12
Boosts
@mttaggart how did you find the model’s performance with Svelte? I haven’t had a lot of success there.
@mttaggart This was a great read, thank you for writing up your experiences.
As someone who is going back to school to transition into the field, the whole topic of AI is intriguing and intimidating at the same time. I am thankful I've been a hobbyist programmer for a long time, so I can recognize when it feels bad to use, along a lot of the lines you wrote about.
This comment is unavailable — it may have been deleted or is not visible to you.
This comment is unavailable — it may have been deleted or is not visible to you.
@glyph I'm curious about why you have reservations about the purity section, or, to put it another way, why it apparently did raise your hackles to some extent. @mttaggart
@matt @mttaggart "ideological purity" is a bit of a loaded phrase. While I'm sympathetic to the *sentiment*, I don't think it's true that "purity is a weapon used to divide labor against each other"; the thing that was used to divide labor against each other was racism. Now… purity does come into that, because once a bunch of racists are wandering around your movement, you've got difficult choices to make about how you maintain your coalition.
@matt @mttaggart so, like, you could argue that it's "purity testing" to say that racists are unwelcome in your movement, and that we can't fight amongst "ourselves", except that the opposite of that is to welcome racists into the coalition and now it's just a coalition of racists because the racists are going to chase all the minorities out
@matt @mttaggart there's a very delicate line to walk where you don't "purity test" casual racists by being super aggressive to them, but instead you make it clear that while *they* are welcome, their *racism* isn't welcome, so you can try to rehabilitate the casual rubes while aggressively excluding the heartfelt bigots. it's kind of impossible, which is why I am more sympathetic to this sentiment than to other recent formulations of this problem.
@mttaggart I wanted to write almost the same post, as this
> I let this thing into my brain, and now it is always there. For any new potential project, there is a voice in my head telling me how much easier it would be to let the model do it. How much faster it would be to simply describe the objective in a prompt and let go.
is what I'm strugling with now, but you wrote it perfectly
@mttaggart Debates aside, your thorough post was also a charm to read this gem.
"Do I think LinkedIn is the digital River Styx, where damned souls clamber over each other and claw at the boat passing overhead in the dim hope of salvation from those who have escaped the shambling horde?"
Also happy to read it works with Discourse.
@mttaggart
This might the best, most nuanced writeup I have read.
@EricCarroll Wow, thank you so much! I really appreciate that, and you taking the time to read it.
@mttaggart really excellent write up! Thanks for taking the time to do it
@mttaggart I feel very similar and have gone down a similar path recently. For me I've found it does very little wrong for the apps I am trying to make and I am more eager to press 2 because I enjoy the outcome and testing that outcome more then have control over the code.
I've been calling myself a self loathing AI user but I'm in the process of building 5 or 6 apps and tools I have wanted over the years but never found the effort to do.
@stefan would you be willing to share one example? The kind of app that you would want to build that you need to use this claud. What would be the difference of you doing it vice the ai doing it? Thank you.
@skykiss I just launched this mastodon client that is focused on live blogging. This probably would have taken me weeks or months to get it to the state I have gotten it in in just 2 weeks.
I certainly didn't need calaude to do it technically... but I did need it to lower the effort bar low enough that I actually got code committed to repo.
@stefan Thank you for sharing that experience, and thank you for reading!
@mttaggart "the best way to be pickled is to stay in the brine" - Gerald M. Weinberg
We are all in the brine now. Does the brine evaporate fast enough, or does it thicken?
@mttaggart thanks for writing this!
Thanks for posting this, it was very insightful.
The human factors issues you raise are important. They strike me as similar to issues with autopilot systems in aviation. If the human-in-the-loop is left with nothing more than tediously approving automated functionality then at least two problems emerge: 1) the pilots lose valuable skills that they may need in life-or-death situations, and 2) the pilots are lulled into stupor as they mindlessly monitor a stream of automated behaviors and fail to recognize and react to problems that are rare events.
The aviation industry's response has been to require manual piloting periodically to maintain proficiency, along with perhaps other interventions that I'm unfamiliar with. I'm not sure what this would look like in practice for software development. Maybe requiring developers to manually generate some features? Maybe intentionally inserting mentally-engaging tasks in the human-in-the-loop code review process?
@DaveMWilburn @mttaggart a key difference between aviation and autopilot and software development and slop is that piloting an aircraft is a life-or-death situation and the autopilot has a very constrained task and a real-time deadline, whereas the LLM (being sold to us as some kind of a general task-accomplishment system) just shits out garbage code fast and all i'm doing is creating unreadable software for future people to have to deal with, under an extremely false pressure to perform
@atax1a @DaveMWilburn I have some bad news for you about where that code is going.
Yes, the stakes can indeed be life and death.
@mttaggart @atax1a @DaveMWilburn *cough*MCAS*cough*
@mttaggart @DaveMWilburn well yes we understand that some code is life-or-death stakes but in that case you REALLY want that to be written my someone and not extruded from a probability model. and vibecoding is more likely to introduce reliability problems than solve them. hence the contrast between the open-ended "generative" machine versus the specific-purpose, known-task system.
@DaveMWilburn We're dangerously close to trade guilds and licensure here, which... yeah maybe?
@mttaggart Very well written and considered, thanks!
@davebauerart Thank you! Appreciate you reading!
