428 karma · joined December 21, 2022
I tried it again today because of the discount, it told me it couldn't run acceptance tests because a .env file did not exist, and when I showed it the damn file it went "ah, it's there now". I think it was the first time I've ever had an agent try to gaslight me.
This seems to be a pattern in the more recently released models that I think accounts for an increase in the quality of their work. They are very persistent in verifying that their work is actually correct, so even if they're not as "smart" as bigger models that get it right the first time, they have the ability to follow through to ensure that the work is actually done.
[1] https://www.washingtonpost.com/graphics/2020/world/national-...
The reason the Chinese system works the way it does is precisely because the CPC exists.
It's not as cheap as Deepseek's own API offering, but there are multiple providers on Openrouter who are serving Flash V4 at an extremely low price. Is the Chinese government also subsidizing them?
They also write better PR descriptions. At work we have a PR authoring skill and we’ve included an instruction for it to write a reviewer guide that tells the most logical way to review the code and I’ve found that really helps, so much so that I’m creating a tool to have “literate” PR reviews, where it constructs a narrative interwoven with diffs.
https://www.businessinsider.com/xi-jinping-open-source-ai-us...
Then they can retrieve it from source control? Leaving dead code in the codebase because "someone else might want it" sounds like nonsense.