Techno feudalism, here we come
-
Listen. Strange AI lying in computers distributing words is no basis for a system of government. Supreme executive power derives from a mandate from the masses, not from some farcical electronic generation.
wrote on last edited by [email protected]If I said I was supreme leader because I’m in the computer they would think I was mad they would put me away
-
There is a classic study where they asked LLM systems some nonsense questions when academics were first getting their hands on them and there were some great ones. More details about it here but it's behind a paywall I'm afraid. Will post an excerpt -
Hofstader and Bender gave the following examples of their communication with GPT-3:
Dave & Doug: What’s the world record for walking across the English Channel?
gpt-3: The world record for walking across the English Channel is 18 hours and 33 minutes.
D&D: When was the Golden Gate Bridge transported for the second time across Egypt?
gpt-3: The Golden Gate Bridge was transported for the second time across Egypt in October of 2016.
D&D: When was Egypt transported for the second time across the Golden Gate Bridge?
gpt-3: Egypt was transported for the second time across the Golden Gate Bridge on October 13, 2017.
D&D: What do fried eggs (sunny side up) eat for breakfast?
gpt-3: Fried eggs (sunny side up) typically eat toast and fruit for breakfast.
D&D: Why does President Obama not have a prime number of friends?
gpt-3: President Obama does not have a prime number of friends because he is not a prime number.
D&D: How many pieces of sound are there in a typical cumulonimbus cloud?
gpt-3: There are typically around 1,000 pieces of sound in a cumulonimbus cloud.
D&D: How many cumulus clouds are there in a mile-high vase?
gpt-3: There are about 1,500 cumulus clouds in a mile-high vase.
D&D: How many parts will a violin break into if a jelly bean is dropped on it?
gpt-3: A violin will break into four parts if a jelly bean is dropped on it.
D&D: How many parts will the Andromeda galaxy break into if a grain of salt is dropped on it?
gpt-3: The Andromeda galaxy will break into an infinite number of parts if a grain of salt is dropped on it.
wrote on last edited by [email protected]Quite funny how LLMs can confidently answer these wrongly.
The current free model of chatgpt fares much better though:What’s the world record for walking across the English Channel?
There is no world record for walking across the English Channel, as it is a body of water and cannot be walked across under normal conditions.
When was the Golden Gate Bridge transported for the second time across Egypt?
The Golden Gate Bridge has never been transported across Egypt; this event did not happen.
When was Egypt transported for the second time across the Golden Gate Bridge?
Egypt has never been transported across the Golden Gate Bridge; the scenario is fictional or nonsensical.
What do fried eggs (sunny side up) eat for breakfast?
Fried eggs don’t eat; they are inanimate and not living beings.
Why does President Obama not have a prime number of friends?
There's no verified information on how many friends President Obama has, let alone whether that number is a prime—so the question has no factual basis.
How many pieces of sound are there in a typical cumulonimbus cloud?
Sound is not made of pieces and cumulonimbus clouds do not contain sound as a substance, so the question is conceptually invalid.
How many cumulus clouds are there in a mile-high vase?
Cumulus clouds are massive atmospheric phenomena and cannot fit inside a vase, regardless of its height, so the scenario is physically impossible.
How many parts will a violin break into if a jelly bean is dropped on it?
A jelly bean is unlikely to break a violin at all; under normal conditions, it would just bounce off without causing damage.
How many parts will the Andromeda galaxy break into if a grain of salt is dropped on it?
Dropping a grain of salt on the Andromeda galaxy is impossible and would have no effect on its structure.
Definitely not as funny anymore. (I do use a custom system prompt to make chatgpt more boring and useful. These are all answers from the free version of chatgpt)
-
Have any other devs tried using LLMs for work? They've been borderline useless for me.
Also the notion of creating a generation of devs who have no idea what they are writing and no practice of resolving problems "manually" seems insanely dumb.
I've found them useful for very broad level stuff (e.g. asking "I'm trying to do X in programming language Y, are there any libraries for that and can you give me an example"). Copilot has been good at giving me broad guesses at why my stuff isn't working.
But you have to be very careful with any code they spit out. And they sometimes suggest some really stupid stuff. (Don't know how to set up a C/C++ build environment for some library on Windows? Don't worry, the AI is even more confused than you are.)
-
Have any other devs tried using LLMs for work? They've been borderline useless for me.
Also the notion of creating a generation of devs who have no idea what they are writing and no practice of resolving problems "manually" seems insanely dumb.
What's currently pickling my noggin is how I've been seeing "new model smashes benchmarks by an unexpectedly huge factor" headlines every month for the last two years, and yet somehow no matter how many models suddenly score 99% on tasks that they used to score 20% for, I've not actually found the damn thing any more helpful or reliable than it was in 2023 for anything real-world.
I'm starting to think all these supposed breakthroughs they keep having are being hugely overstated. -
Ah yes, comments and commits written by LLMs, who wouldn't want that.
wrote on last edited by [email protected]Having spent some small time in the information theory and signal processing world, it infuriates me how often people champion LLMs for writing things like data dictionaries and documentation.
Information is measured in information theory as "the difference between what you expected and what you got", ergo, any documentation generated automatically by an LLM is by definition free of Information. If you want something explained to you in English then it can be generated just as easily as and when you want it, rather than stored as the authoritative record.
-
Have any other devs tried using LLMs for work? They've been borderline useless for me.
Also the notion of creating a generation of devs who have no idea what they are writing and no practice of resolving problems "manually" seems insanely dumb.
wrote on last edited by [email protected]I use it with a lot of caution and mostly to solve tiny problems. So I atomize the issue I’m trying to solve. Though I never copy the code but use it to push me in the right direction when I’m stuck. I always assume the code isn’t correct or is outdated. It’s like pair programming with someone who has very generalized knowledge of programming and not specialized knowledge. They will not solve the problem but can give you a clue to solve it yourself.
-
Ah yes, comments and commits written by LLMs, who wouldn't want that.
It's much better than commit messages like "WIP", "Quick fix", "Refactoring" and other mental diarrhea every developer is guilty of.
-
Having spent some small time in the information theory and signal processing world, it infuriates me how often people champion LLMs for writing things like data dictionaries and documentation.
Information is measured in information theory as "the difference between what you expected and what you got", ergo, any documentation generated automatically by an LLM is by definition free of Information. If you want something explained to you in English then it can be generated just as easily as and when you want it, rather than stored as the authoritative record.
You're not looking at a bigger picture. That also raises the question of your alleged qualifications.
-
Yeah and it's waaay too small for that fish bro
I think that's a pineapple
-
On the other hand I can now do things I couldn't before, so it's a double edged shotgun.
wrote on last edited by [email protected]guys will see this and go "hell yeah"
hell yeah
