this post was submitted on 05 Oct 2024
428 points (96.9% liked)

Programmer Humor

32537 readers
288 users here now

Post funny things about programming here! (Or just rant about your favourite programming language.)

Rules:

founded 5 years ago
MODERATORS
[email protected]
[email protected]
428
How can I mock AI in jest (lemmy.world)
submitted 1 month ago* (last edited 1 month ago) by SwordInStone to c/[email protected]
27 comments fedilink hide all child comments
 

Context: jest is a Javascript testing library, mocking is something you do in test in order not to use production services. AI understood both terms in a none programming context

top 27 comments
sorted by: hot top controversial new old
[–] [email protected] 159 points 1 month ago (4 children)

Man, it really is like an extremely dense but dedicated intern. Does not question for a moment why it's supposed to make fun of an interval, but delivers a complete essay.

Just make sure to never say "let's eat Grandpa" around an AI or it'll have half the leg chomped down before you can clarify that a comma is missing.

[–] [email protected] 42 points 1 month ago

Yea I didn't think about that but if someone said to an AI powered robot "Hey, can you shred my reports?" as they leave work they could easily come back in the morning to it tearing their junior staff into strips like "Morning boss, almost done".

[–] CoggyMcFee 19 points 1 month ago

“How do I help my uncle Jack off a horse?”

[–] Ptsf 5 points 1 month ago (1 children)

Also never ask it to solve a picture of a crossword.

[–] [email protected] 6 points 1 month ago (1 children)

how's that?

[–] Ptsf 6 points 1 month ago (2 children)

Not great, honestly.

[–] [email protected] 4 points 1 month ago

Yeah, this is the problem with frankensteining two systems together. Giving an LLM a prompt, and giving it a module that can interpret images for it, leads to this.

The image parser goes "a crossword, with the following hints", when what the AI needs to do the job is an actual understanding of the grid. If one singular system understood both images and text, it could hypothetically understand the task well enough to fetch the information it needed from the image. But LLMs aren't really an approach to any true "intelligence", so they'll forever be unable to do that as one piece.

[–] [email protected] 1 points 1 month ago* (last edited 1 month ago) (1 children)

Well tbf this isn't what chatgpt is designed for. It can interpret images and give information/advice/whatever, but not solve ~~puzzles~~ crossword puzzles entirely.

[–] Ptsf 3 points 1 month ago (1 children)

🤔

[–] [email protected] 4 points 1 month ago* (last edited 1 month ago) (1 children)

There's a difference between helping to solve puzzles and actually solving them.

You have to be more specific:

[–] Ptsf 2 points 1 month ago

I later did ask it to just be helpful, specifically requesting it give me some possible words that fit for the 5 letter possibility for #1. It repeated "floor it" lol.

[–] [email protected] 54 points 1 month ago

As much as I'm still skeptical about "AI taking all of our jobs" anytime soon, interactions like these still blow my mind...

[–] [email protected] 30 points 1 month ago (3 children)

That first one reminds me of a part of HHGTTG where I think Ford starts counting in front of a computer to intimidate it because its like walking up to a human and chanting "blood, blood, blood".

[–] SwordInStone 31 points 1 month ago (1 children)

For those as confused as I: HHGTTG = The Hitchhiker's Guide to the Galaxy

[–] obinice 23 points 1 month ago (1 children)

You sound like a hoopy frood that knows where his towel is

[–] SwordInStone 13 points 1 month ago

I'll take that as a compliment it obviously is

[–] [email protected] 9 points 1 month ago

How I Hit your Grandma Today, Thank God

[–] [email protected] 5 points 1 month ago

To be pedantic, Ford's threat is to "rearrange [the computer's] memory banks with an axe"

The countdown is until he starts doing it.

[–] [email protected] 25 points 1 month ago

Why do i read it out in Codsworth voice in Fallout 4

[–] [email protected] 20 points 1 month ago

ChatGPT has gotten scary good with both entirely misunderstanding me in almost the exact way my ND ass does to NTs AND with how well it responds to "no, silly, and please remember this in future"

I don't use it super often, but every 6mo or so and it's gotten crazy good at remembering all my little nuances when I have it so shit for me (nothing like research, mostly "restructure data in format a to format b pls")

[–] 9point6 12 points 1 month ago (1 children)

No. 5 was a fun mental image

[–] TragicNotCute 7 points 1 month ago

callback executed

💃

[–] JATtho 10 points 1 month ago (1 children)

The point when the AI hallucinations become useful is the point where I raise my eye brows. This not one of those.

[–] JustARegularNerd 3 points 1 month ago

In this case though, it's not a hallucination, there's nothing false in that response, it just completely misinterpreted what the user was asking.

[–] [email protected] 7 points 1 month ago

LLM got jokes! This had me in tears. Best AI response I’ve ever read hands down.

[–] nroth 4 points 1 month ago

I would have interpreted this the same way as the AI did FWIW. Then again, I don't do frontend stuff, and I run when I see TypeScript in my hobby projects because it's such a pain.