same, i really dislike opencode's UX. there are a lot of agents harnesses actually. check out terminal bench 2.0 for example. dirac.run seems to be make the rounds earlier

The hashing and other optimizations in Direct seem kind of brilliant in a "it was obvious (once someone already thought of it)" kind of way, but the active avoidance of MCP seems weird when that and agent plugins are by far the easiest ways to reuse skills now.

google's the middleman, and it won't capture the whole 1600 right?

No. They are saying 1605 USD is the average amount Google make from a user in the US.

you are missing the picture here. would you then agree that agentic + selection is better than hand-written + selection? in that case, even if the advantage is project selection, nobody would choose to work in a hand-written way right?

unless the 5.4 price is a huge loss leader for them

probably the wrong take - they are arm racing to a better model. it's not enshittification era for models just yet

Models are still in arms race mode, but harnesses and subscription strategy are tiptoeing into their enshittification era.

obviously no. if algos work in china, it will work with spacex

make the point directly - you are just avoiding further justification

can you also add a way to allow it to be used without screen-recording permissions?

are you sure other forms of language to express urgency doesn't work as well or better?

They're just words. It's not a person. It doesn't "understand" anything. (I sound like the bad guy in a robots-have-feelings movie)

I've also tried giving LLMs religion to much more limited success (haven't figured out the right way yet).

I'm manipulating a language model, not a person. "fuck you" translates into a vector in a really big space, and it has different results than being polite about it.

In that prompt I'm reenforcing a directive in five different ways

- idgaf about risk

- you coward

- waste some time

- just do it

- stop bitching

This cluster of instructions are all related but in slightly different directions, are unambiguously strong, attention grabbing, and direct and the model does not argue or get confused about intent

In this particular instance this was the fifth time I had given a particular instruction only to have it subverted by the model that had decided "that's too hard I'm going to do something else instead" in four separate ways.

Abusive cursing did indeed work better than any other form of urgency or insistence.

yes speech to text exists