Not to mention that there are differences in ecosystem, familiarity, and ergonomics that may make a team want to stick with Python.

“Just use Go” is not really actionable advice in most cases.

If it’s very large, especially if the tool needs to refer to documentation for a lot of custom frameworks and APIs, you often end up needing very large context windows that burn through tokens faster.

If it’s smaller or sticks with common frameworks that the model was trained on, it’s able to do a lot more with smaller context windows and token usage is way lower.

They’ll still use even smarter LLMs badly no doubt, but I’m thinking that maintainers of open source projects will be able to more effectively use LLMs to review potential PRs to weed out the truly bad ones quickly.

It’s obviously an imperfect rule, and maybe it’ll change over time. But I am just saying that I understand why open source maintainers are doing this.

There is just no possibility for them to review all the low effort AI slop being thrown their way. Yes, some of it is going to actually be very high quality, but you don’t know that until you review it, which is the whole issue.

Maintainers should get to spend their time developing stuff, not just reviewing low effort PRs. The flood of LLM code is changing the balance for the worse for maintainers, and I can totally see why they’d just want to ban it.

Much of the token usage is in reasoning, exploring, and code generation rather than outputs to the user.

Does making Claude sound like a caveman actually move the needle on costs? I am not sure anymore whether people are serious about this.

To me, caveman sounds bad and is not as easy to understand compared to normal English.

Maybe using a heartbeat to detect live sessions to cache longer than sessions the user has already closed. And only do it for long sessions where a cache miss would be very expensive.

Why bother with all that when you can simply charge an extortionate rate and customers will pay it anyway because it’s still profitable?

There is no real barrier to a customer of Anthropic adopting a competing model in the future. All it takes is a big tech company deciding it’s worth it to train one.

On the other hand, Visa/Mastercard have a lot of lock-in due to consumers only wanting to get a card that’s accepted everywhere, and merchants not bothering to support a new type of card that no consumer has. There’s a major chicken and egg problem to overcome there.

I’m assuming you can cram more chips in there if you have more efficient chips to make use of spare capacity?

Trying to measure the actual compute is a moving target since you’d be upgrading things over time, whereas the power aspects are probably more fixed by fire code, building size, and utilities.

People who do this want the fun part of pretending they’re implementing a feature without actually putting in the hard work it takes to make something for real.

They want the repo maintainers to do all the hard, boring parts while they have fun. As if maintainers of open source projects don’t have enough thankless work on their plates. Good luck with that!

Most publishers of content online are ad supported and struggling, and I want to make sure I’m contributing to their revenue somehow.

I don’t feel bad about blocking ads on sites I pay for though.

Such as news and magazine sites, many of which are actively dying due to a lack of revenue.

I personally wish these sites could all switch to paid models, because I also don’t like ads.

But absent that, I’d like to support the sites I use so that they don’t go out of business.

Where’s the value added if the person just tells Claude to do it and then submits a PR?

The maintainers may as well vibe code it themselves if that’s all the work the would-be contributor is going to put into it.