> Letting the model run feels like giving up control, while inventing a workflow feels like the responsible move, even when it produces worse work in more time.
It feels to me like the discretion of the humans is the main problem in your solution space example.
Some tasks require more structure than others. Sometimes, the constraint a human faces is “you must do the work in this module or on this function”.
If the prompt says “only change this function” then the human has a good reason for that. If the LLM can’t figure it out then letting them cook on it feels like a waste of my time and tokens.
Too often I’ve sent Opus or Fable now on what I thought was a simple task to find it chasing its tail.
Fortunately I find more success than tail-chasing with the LLMs but I’m dubious of any suggestion to just let them cook.
However, a solution to the tail-chasing for certain could be to intentionally expand the solution space and to consider how my prompts might be restricting the LLM’s options.
The US has the highest per-capita rate of imprisonment I think we’re plenty “hard on crime”. What we lack is a principled stance that Americans deserve basic dignity and access to things that make people live less violent lives. It’s no secret that poverty is the key contributor to one’s likelihood of being in prison.
People who are “soft on crime”, practically speaking, are the people and politicians so committed to dehumanizing others that they’d rather watch their neighbors wallow in poverty or rot in jail than to actually do something to address the root causes (the foremost of which being the aforementioned societal dehumanization of the poor).
The number of blogs posted on here by people who can’t be arsed to make their writing legible on mobile blows my mind. Did everybody just skip the section of their CSS journey that covered media queries or what?
I enjoyed the article but it was a nightmare to read on my phone’s browser
I think it was more about doing it without a Boolean-based branch construct like a ternary or switch or whatever flavor of thing that abstracts away the explicit checks for true/false by other means. Idk though for sure
> they want to maximise the time people spend on their apps so that they can sell this attention to advertisers
This is where they manipulate in my mind. They maximize that time by exploiting human psychology, manipulating people into scrolling their feeds endlessly eh?
“what it does” describes the actions taken - cancer wards work to treat cancer (which is their purpose). Outcomes of what they do isn’t relevant to the point.
The purpose of most social media companies is to manipulate people for financial and political gain which is what they do.
Strudel can use custom samples in addition to the built in synths and samples. The language is really expressive. I’ve not gone too far into playing with it but from what I’ve seen it’s pretty flexible.
That said I’ve only seen people making house/techno/drum-n-bass kinda stuff with it.
The only people who matter are shareholders. Employees are a means to the end of making money for the owners of the company whether through stocks or other kinds of ownership.
What’s wrong with this from your perspective? IMO it’s too little too late and should have been a federal law years ago.
Don’t get me wrong - Newsom is a slippery snake politician and is beholden to rich scumbag donors but I don’t see how this in particular is due to his and the dems big donors.
That said you seem to imply that only one side of this shitshow is beholden to big donors but corruption and general degeneracy is far more prevalent in the elephant party.
I’d guess that it’s because React came around and it was from Facebook so it got a lot of adoption? Maybe there’s some other reason, the comment you responded to seems to imply something anyway
It feels to me like the discretion of the humans is the main problem in your solution space example.
Some tasks require more structure than others. Sometimes, the constraint a human faces is “you must do the work in this module or on this function”.
If the prompt says “only change this function” then the human has a good reason for that. If the LLM can’t figure it out then letting them cook on it feels like a waste of my time and tokens.
Too often I’ve sent Opus or Fable now on what I thought was a simple task to find it chasing its tail.
Fortunately I find more success than tail-chasing with the LLMs but I’m dubious of any suggestion to just let them cook.
However, a solution to the tail-chasing for certain could be to intentionally expand the solution space and to consider how my prompts might be restricting the LLM’s options.
Enjoyed the blog thanks for sharing!