> The fastest moving and most effective organizations I've worked at are ones that focused on code quality from the beginning.
I agree with that in the pre-LLM world, but I don’t believe it’s the same today.
You can build something with “bad” code that works and is full of technical debt, but today paying this debt is getting cheaper and cheaper.
So if Claude’s wrong design decision leads to having to refactor several chunks of a codebase in order to implement a new feature, does it really matter if it’s Claude who is going to refactor it in a matter of seconds? Especially for a company like Anthropic which has a virtually unlimited number of tokens to spend on it.
Sounds like converting technical debt to monetary debt that will still ultimately need to be paid. Pay engineers and/or anthropic to fix the problems caused by anthropic. What do you do when anthropic servers are down?
I started coding around 2013, picked up a book, learned Java and started building Android apps. It was fun at the time, and pretty painless to get your app in the store.
Fast forward to last year, with all the rage about coding tools, I got into building small projects again, and built a simple app. After a decade from posting my last app on Google Play I resurrected my account, and started going through the process of publishing an app today... And how awful things got!
Back then it was essentially, title, description, upload your Apk and some screenshots and you're done! Now there are reviews, privacy policy, endless amount of forms and information you need to fill out. I get why (some) things are the way they are today, but when you just want to make an app for fun, getting it out there just feels like work. I gave up on the app, made it into a website, and in the end it actually felt better (and so much easier).
Try 3.8 27B in MTPLX; I get about 30 tok/s with the same hardware as you. (Although it does use around 90-95W of power, compared to the ~60W that 3.6 35B-A3B uses to generate 55 tok/s. That’s about 3 J/tok instead of 1.)
I was interested in learning more about reverse image search, so I built audioguide.london. It’s a simple image search where you take a photo of an artwork in a gallery, tries to ID it and returns a pre-generated audio and a link to the museum website.
The audios were all generated locally, essentially looking at the contents of the website, running it through a LLM to generate a script and Kokoro for TTS.
I’ve built it as an app for myself almost a year ago, so I deployed it as a vibe coded website in here: https://audioguide.london/
I agree with that in the pre-LLM world, but I don’t believe it’s the same today.
You can build something with “bad” code that works and is full of technical debt, but today paying this debt is getting cheaper and cheaper.
So if Claude’s wrong design decision leads to having to refactor several chunks of a codebase in order to implement a new feature, does it really matter if it’s Claude who is going to refactor it in a matter of seconds? Especially for a company like Anthropic which has a virtually unlimited number of tokens to spend on it.
reply