Remix.run Logo
▲ raincole a day ago

Explaining what they want to an LLM - something that can understand badly organized word salads with infinite patience - is frustrating? Then imagine how they'd feel if they have to explain what they want to a human...

▲jazzypants a day ago | parent | next [-]

The key differences are that humans can better anticipate people's needs, communicate through body language, understand social cues, maintain critical information even as it changes quickly, and interact with the real world effortlessly.

▲nextaccountic 19 hours ago | parent | next [-]

Intellectually, I don't see how humans will stay better at anything for too long. And with a bit of robotics, I don't see how humans will stay better at manual work either I'm talking about 10+ years down the road, a blip in the history of humanity. We don't stand a chance.

Capitalism is inherently broken if people don't get paid wages, because then they don't have money to buy stuff. Fortunately, capitalism doesn't need to exist forever

▲b112 a day ago | parent | prev [-]

For now. Wait a couple of years.

▲ratelimitsteve a day ago | parent | prev | next [-]

"I want it to search and be fast"

vs

"I want to pre-sort during idle time so that I can effectively implement a binary search"

You can tell me either of these and get the same product. You can pick one of these and tell an LLM to do it three times and get three different products.

▲blobbers a day ago | parent [-]

And the LLM can also implement something way better than idle pre sort.

Sorry, this cope.

▲tyg13 a day ago | parent [-]

Left to its own devices, the AI may choose to implement things efficiently and correctly, or it may choose to implement things inefficiently and incorrectly. Without clear guidance, acceptance criteria, and hand-holding, it will make assumptions that are wrong, and as the demands of the product grow, it will continue to build off of those wrong assumptions. This is my experience with Gemini, Claude, GPT -- any of the models. They need guidance or they will build crap.

Now, this may be acceptable (tons of businesses are built on broken products), but what is absolutely cope is this moronic idea that the LLM is always smarter than the average engineer and will magically produce the most efficient and correct solution.

▲ratelimitsteve a day ago | parent [-]

> Without clear guidance, acceptance criteria, and hand-holding, it will make assumptions that are wrong

Yeah but the person you're replying to isn't gonna see that because they already made several assumptions about the problem I put in front of them

▲techpression a day ago | parent | prev | next [-]

A big part of the job is to not have them do that though.

▲bigfatkitten a day ago | parent | prev | next [-]

There is an entire profession of people who make good money doing this for a living. They are called business analysts.

▲dominotw a day ago | parent | prev [-]

Are you saying you presonally explained all your needs to apple to get the laptop or phone you used to type that comment?