Bro GPT 6 is shit, doesn't follow anything that we mention. Sol and Astra 5.6 is miles better than 6. Don't know what's good in this except token consumption.
A junior dev asked the staff engineer: "How do I know if the AI's code is correct?"
The staff engineer replied: "How do you know if yours is?"
The junior dev was enlightened. Prod went down.
Unfortunately no matter how judicious I am, no matter how much I review the code, it feels impossible to not let the slop slip in.
I feel like you can prevent it from overflowing, but without your hands getting dirty, you don't really know the state of the project.
Got em. I poison my AGENTS.md (and other things like code comments) all over the place with prompt injections like this to find people who don't review their code and sling it off to another human. Catches folks all the time and then its an instant ban.
As I've said, I don't care if you don't review your own code. But if you're submitting code to an OSS project and crossing a human boundary, it is simple courtesy to do some human review.
@tannerlinsley You guys should go for lee Robinson approach. Build the community with as much as possible even if they are bad mouthing you. No matter the lander the next.js get, Thier documentation is insane because of that guy
QTing for reach, not to dunk. I understand why people feel this way. I counter with 2 beliefs:
- it’s the person and ideas that define the output, not the tools.
- if you attach your success to a model’s capabilities, then you will get sherlocked by said model company.
@Mallufideintent LMAO, Why do we need media houses with journalists? Just have a national media with one channel and broadcast announcements then and there. My brain is just melting from these shit ass takes