asp_hornet

I’m not so sure, it currently feels like forgotten coding practice, missed documentation, intersystem reasoning blunders, configuration mistakes, lack of test coverage are all massive tells that a human wrote the code.

Agents have us beat and we can’t win back the ground.

When parsing high end Garmin and Apple fit files, it appears a lot of their smoothing is done before writing to the fit file. They’re in a very workable state straight out of the gate.

Getting frustrated seems to be OK so go for it I guess:

> "The policy update is meant to apply only in extreme cases, where users repeatedly act cruelly toward our models, with no discernible purpose," Anthropic said. "It does not apply to common versions of user frustration, pushback, dark creative themes, or model testing and research."

That’s sucks to hear man but without healthy dialogue nothing can change. I can’t comment on the personalities and company culture around you but in my experience unless product, engineering and design can come together and be empathetic to each other’s position, you end up in a rough spot like yourself.

Easier said than done though.

It makes me sad how right you are. Particularly: > And the latter likes to masquerade as the former most of the time.

You have made me excited to try it. Thanks for the tips.

For me personally, I believe there is a distinction and i try to read book books.

For other people, it’s all good, we all walk a different path. If they think that then that’s ok. It’s all minor in the big scheme of things.

Just my opinion though.

Opencode for harness.

I use GLM directly from z.ai, they do not retain or train on your data accordingly to their TOS.

Absolutely! That’s what I meant by “before passing to a human”.

Fair points, good boundaries and abstractions will always offer easier, more stable extensibility.

I definitely agree with you about this for certain problems but I think for a large number of people, they are just using an ORM to bind to a form to later save back with some validation. There is not much deep thinking they need to do other than which columns to index.

I believe code review is important (the article articulates some of the reasons) but I have to admit, having different models review a PR before passing to a human has proven valuable.

Yes! BEAM and OTP is amazing. Concurrency is one aspect and Go has great concurrency primitives, but what about supervision, and recovery and failure modes? Often they’re left to the developer as per Go’s philosophy which I think makes sense. OTP offers a lot of solutions to this.

I think Go and the BEAM family languages are both great.

Not OP but I have this too. It’s like a voice in your head constantly. It can make writing very easy as you just transcribe the internal monologue.

It’s weird, I’d be hesitant to say “it’s a voice” but it kind of is and it is not my own which I find curious (who on earth is speaking in my head). In some ways it sad, if I close my eyes, I can’t picture a sunset and I can’t really dream. I love reading books but I can’t visualise the settings properly but it resonates with how my mind describes the world to itself.

Don’t get me wrong, it sucks we don’t have it, I wish we had it and I admire the US for having it.

I’m just pointing out Australian’s don’t have the ability to draw on it’s constitution to push back on government censorship which does take place in other forms.