Many of us are now using coding agents everyday and, it would seem, GitHub pull requests are developing a bit of an accent as a result.
An analysis of 47,000 PRs found a distinct vocabulary cluster dominated by words like “load-bearing,” “quietly,” “latent,” and “genuine" that grew from 1% of the corpus in January to 45% today.
The project samples 100 PRs a day, filters out bot and agent accounts, and groups descriptions into eight different writing styles based on word choice. For those of us familiar with their work, this cluster certainly sounds like the "load-bearing" vocab of LLMs.
https://t.co/4PeC2mPZ23
The thing I miss the most about coding by hand is the clarity.
You knew exactly what lives in which file, why you wrote a specific line, why you rewrote the other one, why you used this library.
You still can have such awareness, but it’s harder since everything happens faster
@Lindstar24 Misleading. UC doesn't pay a couple's allowance per wife, a second wife claims as a single person. Housing Benefit has a small extra-spouse amount, and the benefit cap still applies. The £78,000 is separate people's claims added together.
Someone asked me why I think this is ridiculous, and here is my answer:
Because the tool used to accomplish a task is irrelevant
What matters is the quality of the work
The idea that AI work needs to be distinguished from human work is adjacent to the marxist theory of value
When someone digs a ditch in your yard, do you care if they do it by hand or use a machine?
Or do you only care that they do the job properly?
The problem with Anthropic is that they do not see machines as tools to be used by humans
They think in their kooky cult that they are making a new type of life
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true:
○ You’re a beginner
○ Software is throwaway
○ You’re prototyping
○ You have no users / revenue
○ You’re taking on debt & risk
○ Your problems are basic
And btw. All of this is fine. But the reality is that models are still not at the “full autonomy” stage yet.
They make rookie mistakes, they go down bad architectural paths. I just had the best model in the world add a nonsensical 700ms delay to “settle” something and it told me “you’re right, I was cargo-culting” 🤨
I am on the camp that this need will diminish more and more. Most code is indeed going to be assembly-like. But we also have the global internet and software infrastructure riding on these models and narrative, and we have to respect that.