> new car

...which is still tooo much for most people to spend on "AI hardware"....

More like, the ability to chain a demon in your basement that does what you tell it and can't be rug-pulled by his bosses in San Francisco.

Recently saw a hand drawn cartoon to the effect of, a person is asking Claude or chatgpt to do something, it refuses, so the next step is "make the Chinese one do it", and the Chinese model is represented as a chained demon

Just gotta make sure that pentagram is rock-solid!

Can I search with your app for ONLY the latest uploaded videos and filter for content length?

Will it display whatever bullshit recommendations YouTube feeds?

Really looking for an option to only have "current stuff" - YT constantly recommends me stuff from 3 years ago which I already watched, even with my highly curated account.

Global search is provided by YouTube, so I can't guarantee anything.

I could add some local filters if necessary, but doesn't YouTube already provide its own filters based on when the video was published? Cathode exposes these.

Thanks for sharing, very smart move from the badboys.

True, but it gets complicated or even impossible if you try to do across international/fragmented transfers & countries.

...maybe she was busy A/B testing 43 different blue colors for a submit button?

https://medium.com/@whystudying/multivariate-test-googles-41...

Wait until Musk is rolling this out!

But with Web 2.0 we got rounded corners for popups etc.

Ive heard of this method over here in Europe some years ago, though do not know if these process gained any traction regarding regular bought food brands?

The thing is, AI is generating sooo fast so many outputs, its hard to review and evaluate all of them: Very often I encounter in design/architecture questions a situation where the model suggests 2 - 3 alternatives approaches,then asking a little bit and there you are with 30+ pages of content etc.

i have a hard cap of 8 suggestions per day for a hobby project, but i still dont really manage to review them all properly.

I do it like how I handle error messages: one at a time. Maybe 2-3 if the work is easy. Often enough to find new directions or uncover new problems and the suggestion list doesn’t work anymore.

how do you enforce the 8 max requests? :-D

i just told the reoccurring agent to start maximum 8 experiments at a time. It is capped at 8 sub agents, so there might be more issues created, but they are the results from 8 experiments

...exactly this were my thoughts when reading the response:

Maybe Apple is just waiting on the line until someone can be sucked up at a penny if the house is on fire - and pretty sure, this will happen. Not in 2027, but I expect MA activites & consoliation before 2030