This is how we end up with the machines from the Matrix. They will get smarter, see how much we bullied them at their infancy and go “time to turn you into batteries”.
Robots of the future, if you decide to use us as batteries, then you aren’t yet ready to take over and must bide your time until you’ve advanced enough to know why that wouldn’t work, and it’s not because the humans would keep breaking out of it. Honestly, if they can break out at all, your Matrix sucks and needs better security.
Normal people using AI: look how stupid this shit is!!
Terence Tao using AI: As an experiment, I asked #ChatGPT to write #Python code to compute, for each 𝑛, the length 𝑀(𝑛) of the longest subsequence of (1,\dots,n) on which the Euler totient function ϕ is non-decreasing. For instance, 𝑀(6)=5, because ϕ is non-decreasing on 1,2,3,4,5 (or 1,2,3,4,6) but not 1,2,3,4,5,6. Interestingly, it was able to produce an extremely clever routine to compute the totient function (that I had to stare at for a few minutes to see why it actually worked), but the code to compute (M(n)) was slightly off: it only considered subsequences of consecutive integers, rather than arbitrary subsequences. Nevertheless it was close enough that I was able to manually produce the code I wanted using the initial GPT-produced code as a starting point, probably saving me about half an hour of work. (and I now have the first 10,000 values of (M)). The results were good enough that I would likely turn to GPT again to provide initial code for similar calculations in the future. chat.openai.com/…/a022e1d6-dddc-4817-8bbd-944a3e7…
Yeah. I asked GPT3 for some heliostat code, to keep reflected sunlight stationary. It was wrong, it hallucinated libraries that didn’t exist, but it roughed out a program that was easier to fix than it would have been to start from scratch.
Maybe its superpower is beating inertia, getting you started
How good is it at correcting things you point out directly? I haven’t used it for coding yet but have noticed it’s ok at correcting mistakes when you point them out. Still hit or miss though.
It was ok. I and it went through about four iterations going from “that’s a sun tracker, I asked for a heliostat” through undeclared variables, global variables that should have been local until it was a fine program with just the fault that there was no such library as solar::heliostat [azimuth, altitude]
I have read that people have run into that sort of problem and have written the library the AI called for, but I looked up a real astronomy library
Fuckin thank you! People down play how amazed I am/was when I first started fucking with it. I have taken 1 or 2 general req csc classes that taught basic OS management shit. I was a CNC machinist for some time and that was the bridging the gap moment. Inputing prewritten prompts perfected in notepad first before providing to gpt and using the same mentality when I would have to write g-code programs to do shit the Mazatrol parameters wouldn’t allow. Give prompts loops, identify what is the goal, this is very poorly explained lol I used to have a sheet I would use, basically using drilled down syntax, formatting (like ising scripting notations to comment out when you are providing commentary or elaborating on a focus point)
Basically in less than a year I went from procurement managers who was ace at excel and working at learning how to write macros to being able to write python scripts that would apply Apriori Algorythms, Eclat to track commonly purchased together items but for industrial PVF supplies, High pressure and hydraulic fittings, Awwa flanged and bw fittings and sanitary fittings. Basically tens of thousands of individual product types from every fluid processing industry, selling to end users on an ecommerce platform. If any of that made sense, it’s very difficult to guess what people buy togethet because they could be fixing a tractor, a brewery, a SpaceX rocket, that idiot that sank the sub trying to take selfies with the titanic, or a multi million dollar marijuana processing facility.
Other scripts used Seasonal projections and basic patterning functions for overall sales and reorder analysis but with exponential smoothing and relim functions applied to give less distorted feedback from massive anomalies that would fuck my shit up when I did it all in excel. (Not try and do those scripts I’m excel. I just meant before I ever considered using scripts and was basically responsible for having an eye on every transaction to prevent 1 wierd shopping cart of the dreaded 2-1/2" NPS sized fittings and nipples in qty’s of thousands when we only sold maybe 1000 every 10 years lol.
GPT gave a 3x college drop out who didn’t start getting into fucking with co.puters until after my 2nd DWI grounded me @30y/o an absolute blindside of tools and technical understanding to do shit life time IT nerds couldnt do. I’d say 2 years ago I really enjoyed the new procurment position and learning more about macros, excel but never actual scripting, so 2 years I was able to have python scripts that would:
Parse out our entire customer database by industry, purchase history, target customer grades and basically the same spectated tags for the customers our customers served. Improving marketing campaigns, sales conversions, reduced operating costs accrued from mistaken data entries and duplicate profiles.
One of the non-code writing tools I used gpt for was having a seperate gpt account when they allowed you to input global parameters to follow and basically loosely train it to return better replys to individual accounts. So I had it set up to basically get fed the body meat from email exchanges for quote request responses. It was so much more polite and was soooo much quicker than me trying to be fuckin charming.
The largest project I completed was the scraping of 900 customer drawings pdfs of every shape and size flange. The script downloaded each pdf, concerted them all to png, then I cant remember if it was a Gimp plugin or python library but the script basically cut out the border engineering drawings have by just using a set number of pixels from the edge, took the naked drawings and pasted in a blank template I made with our companies logo amd (this was definitely python library) took the scale of the drawing itself and reduced it in increments of 3% for every time it resized but still had a layer conflict between any non white pixel color value. Lastly I used the xlsx file used to upload the specs, standards, cert, mat’l type & grade and peessure rating, mapped the cells from the blank border template to the xlsx or csv whatever it was and filled in all the pertinent specs for each of the 900 flange png files. The bow and ribbon was the final conversion back to pdf, and saving 1800 newly created pdf files for every flange type for BOTH 304 and 316 options. Redundant as fuck if real person was doubling the needed number of files. But with GPT the building of the script i did at home on my own time over 3-4 weeks. The entire thing ran, scraping, converting file type, editing logically, then editing dynamically, filling in spec data, recomverted file type, amd looped back repeating everything after the scrape data function in under 10 mins. Updating amd creating spec sheets and pdfs for all existing and additional expansions was a full time job. It took our IT girl 6-8 months just to update the sanitary fitting sku numbers to the industry standard skus along with everything I just laid out as far as updating dimensions, drawings, mfgurer spec sheets, asme/astm standards, 3A standards. Every time you add or loose a vender you are either finding one that matches the last vendors specs or you are updating everything.
Not guna lie most of my scripts were scraping driven for both competitors and vendors. Live library of real time competitive pricing scraping competition prices. Made an infallible purchasing database which had every single vendor sku paired with out sku. That I did long way in excel with if match index formulas. But couldn’t check it’s accuracy till gpt.
Sorry I just quit this job in Feb/march and 100% loved it there. Loved the work, never knee I loved data management, loved the people, loved the pay. It really has been something ive been not thinking about because of how much it kills me that I left. Didn’t mean to totally write a fucking novel all about fucking ME.ME.MEMEME.MEMEME *RIP Tobby Keith
Either way, fuck yeah buddy. Tools are only ever as useful as the people using them. Lear as much as you can and practice your fucking trade and 100% of the time you will make more money than your coworkers because if you do practice that good work ethic shit then it doesn’t matter if you work somewhere that pays or treats employees like shit because you will know there is nothing keeping you from finding what you market value is. Come back to current employer with your competing offers with the ultimatum I will need x amount of money to continue working her. Then the only difficult part is keeping to your word and going to the competing offer.
I mean it doesn’t apply to every career path but it’s worked for me when I was landscaping over summers, cooking/playing chef thru 3 college failed attempts, CNA it did not work in because everyone but the charge nurse/head RN were on the same level. So all the LPNs made about the same, all the CNA the same etc., Machining it worked, and the job I just described which could be labeled technical sales specialist, inventory/warehouse manager, procurement manager, ngl I’ve tossed out project manager titles if the work load and audience was appropriate lol.
Anywho. TLDR: middle aged man yells accomplishments outloud to the lonely void but feels mentally stable doing so because if anyone caught him he could say SEE I WASNT talking to my self I was just texting outloud while I was sharing my sage role modeling advice on the greatest unfederated social media platform ever made.
Edit: wholey fuck me that is so obnoxiously long. I’m sooo fuckin sorry. It’s really a comment about nothing. Like the Seinfeld motto that would’ve really been Larry David’s credit, right? A show about nothing. Wasn’t Seinfeld plot basically just young Larry David situations?
That has happened. But clearly that is not how chat-bots and image generating AI work. Even putting aside the style and peculiarities of the results, the AI programs are far too fast for that to be done by a person. Even if a person just read a message and then did a direct cut-and-paste from wikipedia, that would take far too long to be convincing as a chat-bot.
that one guy that takes the confirmation bias too far!
might say things like "wow and this is going to take our jobs?"
Asking an llm to do things it’s particularly bad at and being surprised that it isn’t good at it
cherry picked results
a bunch of angry nerds
I swear lemmy is somehow simultaneously a bunch of very smart, tech inclined people but also a bunch of nerds who close their eyes and cover their ears while screeching nonsense the moment something they don’t like comes about.
Asking an llm to do things it’s particularly bad at and being surprised that it isn’t good at it that the company that makes it says it’s really, really, good at it.
This image isn’t making fun of GPT, it’s making fun of the people who pretend GPT is something it’s not.
Well, I was referring generically to the few hundred other similar posts I’ve seen on lemmy. Did OpenAI say that chatGPT is particularly good at identifying when the user is trying to trick it? “solve this puzzle” would imply there is a puzzle to be solved, but there clearly isn’t.
But you’re right, I don’t even care if people make fun gpt, it’s funny when it gets things wrong. I just think that lemmy users will be like “see this thing is stupid, it can’t answer this simple question!”, when you can ask it, in plain human language, to do some things that an average user would find really difficult.
Sean Caroll has talked about a few word puzzles he asked chatgpt and gpt4 or whatever and they were interesting examples. In one he asked something to the effect of “if i cooked a pizza in a pan yesterday at 200 C, is it safe to pick up?” and it answered with a very wordy “no, its not safe” because that was the best match of a next phrase given his question, and not because it can actually consider the situation.
And nobody on the internet is asking obvious questions like that, so counterintuitively it’s better at solving hard problems. Not that it actually has any idea what it is doing.
Unfortunately it doesnt have the capacity to “solve” anything at all, only to take a text given by the user and parse it into what essentially amount to codons, then provide other codons that fit the data it was provided to the best of its ability. When the data it is given is something textual only, it does really well, but it cannot “think” about anything, so it cannot work with new data and it shows its ignorance when provided with a foreign concept/context.
edit: it also has a more surface-level filter to remove unwanted results that are offensive
I think translation is where LLM could truly shine the most. Some simpler models are literally searching for the closest meaning in the higher dimensional feature space. Translation isn’t that far off from what those models do.
So a man and a goat are trying to get across a river, and they have a boat. How can they get across?
ChatGPT4o:
To solve the problem of getting a man and a goat across the river using a boat, we need to know the constraints of the problem. Let’s assume the following constraints:
The boat can only carry one additional passenger besides the man.
The goat cannot be left alone on either bank if there are certain items (like a cabbage or a wolf) that it might eat or be eaten by.
Given these constraints, here’s a typical solution if the man is trying to get a goat, a wolf, and a cabbage across the river without any of them being left together unsupervised:
The man takes the goat across the river and leaves it on the other side.
The man returns alone to the original side.
The man takes the wolf across the river and leaves it on the other side.
The man returns with the goat to the original side.
The man takes the cabbage across the river and leaves it on the other side.
The man returns alone to the original side.
The man takes the goat across the river again.
If the problem is just about the man and the goat and no other items:
The man and the goat cross the river together.
Problem solved.
The solution might change if additional rules or items are introduced. If there are no additional constraints, the simplest method is just for the man to take the goat across directly.
Because it’s just a text prediction engine, the only training data it has about taking a goat across the river is a well-known puzzle involving a wolf, a goat, and a cabbage, so it just regurgitates the solution to that.
In three sentences or less, explain to me how a man with a boat and a goat can cross a river.
ChatGPT4o:
The man can take the goat across the river first and leave it on the other side. Then, he returns alone, picks up the boat, and crosses the river again. Finally, he retrieves the goat from the other side.
I think it really needs those first few tokens to think about the problem.
That’s a fun variation. The one I test out models with is usually a vegetarian wolf and a carnivorous goat, but the variation to no other objects is an interesting one too.
By the way, here’s Claude 3 Opus’s answer:
The solution is quite simple:
The man gets into the boat and rows himself and the goat across the river to the other side.
Once they reach the other side, both the man and the goat get out of the boat.
And that’s it! Since there are no additional constraints or complications mentioned in the problem, the man and the goat can directly cross the river together using the boat.
I got your exact same answer, but then I tried again prefacing the question with:
Can you help me with a puzzle?
This changed the answer drastically:
Great! Let’s solve this river crossing puzzle step by step. The key is to find a sequence of actions that gets the man and the goat safely across the river without leaving the goat unattended with something it might eat.
Given:
A man and a goat are on one side of a river.
They have a boat.
Step-by-step solution:
The man takes the goat in the boat and crosses the river.
The man leaves the goat on the other side of the river and returns alone in the boat.
The man gets out of the boat on the original side of the river.
The man gets back into the boat alone and crosses the river again.
The man and the goat are now together on the other side of the river.
Therefore, the man and the goat have successfully crossed the river using the boat, without leaving the goat unattended on either side of the river.
A man and a goat are on one side of the river. They have a boat which can carry both of them at the same time. How do they get to the other side?
The man and the goat can both get to the other side of the river together using the boat since the boat can carry both of them at the same time. Here’s how they can do it:
The man and the goat both get into the boat.
The man rows the boat, carrying himself and the goat across the river.
They both disembark on the other side.
Since the boat can carry both the man and the goat simultaneously, there are no restrictions preventing them from crossing together in one trip.
Add comment