I've been trying to get ChatGPT to stop adding this kind of fluff to its responses through custom instructions, but to no avail! It's one of the more frustrating parts of it, IMO.
> As Claude and I build new skills, one of the things I ask it to do is to "test" the skills on a set of subagents to ensure that the skills were comprehensible, complete, and that the subagents would comply with them. (Claude now thinks of this as TDD for skills and uses its RED/GREEN TDD skill as part of the skill creation skill.)
> The first time we played this game, Claude told me that the subagents had gotten a perfect score. After a bit of prodding, I discovered that Claude was quizzing the subagents like they were on a gameshow. This was less than useful. I asked to switch to realistic scenarios that put pressure on the agents, to better simulate what they might actually do.
I think this is somewhat overhyped. If you look at the video that actually exists of this character[^1], it's clearly AI slop that falls flat -- honestly kind of embarrasing for the studio to put out. This seems like more of a media stunt than anything.
Yeah; it would have had the added benefit of generating more revenue for the government via increased income taxes ($100k * income tax rate over N years versus $100k only once).
But I think the reality about the H1-B program no one wants to state plainly is that its effectively a system of voluntary indentured servitude, and its important to all of the masters of the program that the visa holders accumulate as little power as possible.
I've advocated for a long time that the fee should be 1:1 to the salary for the position along with a salary floor of $100k/year as it's for skilled work, which is largely historically been a break point. Today, that may be closer to 140 though.
The money generated should go towards grants for US citizens imo though, as it would shore up the "need" for foreign labor. As long as the economy is growing and there is demand it isn't a problem. If there's a legitimate need, then it should be worth the cost.
To those mentioning outsourcing will skyrocket, I doubt that as it's already widely used and there's a lot of additional friction without embedded staff/managers where the work is getting done, and even then.
out of curiosity, what would it look like to take feedback constructively, but not follow it?
i'm asking because (in my experience) executives get hundreds of pieces of feedback and advice. they can't follow all of it, and so they have to prioritize, and their priorities might not overlap completely with those of ICs.
One sign would be occasionally changing course in response to overwhelming employee feedback. If that never or almost never happens, the feedback is being ignored, not taken constructively and not followed.
if a framework has a BDFL, and that BDFL starts getting increasingly political in a polarizing way, then surely it's fair for the community to respond to that.
