Readit News logoReadit News
nostromo123 commented on ChatGPT sends shockwaves across college campuses   thehill.com/policy/techno... · Posted by u/cwwc
lumost · 2 years ago
I think your underestimating chatgpts utility for students. It’s not just a “do the work for me” tool. It’s a “hey how can I improve this paragraph?”, “why is this true?”, “who first created X”, “If you were a mean TA what would you say about this?” Tool.

It wouldn’t surprise me if C students suddenly looked like A students. Their getting proper and timely feedback for the first time.

nostromo123 · 2 years ago
Someone who is that involved and desiring to learn will get an A even without help, and someone who is not will not care enough beyond "do my homework for me".
nostromo123 commented on Nations reach accord to protect marine life on high seas   apnews.com/article/un-oce... · Posted by u/acdanger
O__________O · 2 years ago
No, that’s not true. Rapid change is possible. Majority of world is only 7 connections part, given enough social pressure, it will stop. Having simple messaging is critical, such as if you eat meat, not talking to you, buying from you, voting for you, etc.

One thing that would be useful though is a super cheap test to check if someone has eaten meat recently.

nostromo123 · 2 years ago
Best to just shoot these pesky meat eaters in the name of saving the planet, right? /s
nostromo123 commented on AI could upend the world even more than electricity or the internet   techxplore.com/news/2023-... · Posted by u/rntn
nostromo123 · 2 years ago
Sorry to hear your job is so simple it can be automated away, but for the rest of us there's no big danger.
nostromo123 commented on Sam Altman 'A Little Bit Scared' of ChatGPT, Will Eliminate 'Many' Jobs   businessinsider.com/sam-a... · Posted by u/elorant
fallingfrog · 2 years ago
We should turn it off while we still can. It will most likely eliminate almost all programming jobs, most creative professions, etc. I mean, people keep saying, “oh, but it can’t do X yet.” But it will, and it won’t take long. How long do you think the world will last once anything you could do or achieve can be done better by a machine instantly? What is your purpose then? Why go to school? Why try at all? The great mass of people will descend into hopeless depression once they realize that there is literally no point to learn anything. Nothing that makes you special. Your talents, whatever they are, will become meaningless. No point in learning to play the piano, or draw, or code.
nostromo123 · 2 years ago
A machine can already run better, fly better, play chess better than me... how does that affect me? Zero.
nostromo123 commented on ChatGPT Will Replace Programmers Within 10 Years   levelup.gitconnected.com/... · Posted by u/thereare5lights
nostromo123 · 2 years ago
"Architect systems and database tables from user stories in seconds"...haha, no. This only works for simplistic problems that we got as students to solve on paper during a 2h exam back in the day.

Realistic problem from my own workplace: "Ok, ChatGPT, write clock- cycle exact embedded C code for checking in less than 5ms if firmware on this ARM is working correctly with the sensor described in datasheet.pdf. Detect and implement countermeasures for any EM interference issues due to cable length. Implement it in a generic way so it can work with Atmel and NXP microcontrollers. There is a bug that caused the sensor to sometimes return wrong values when using the system on a Kuka xyz robot, please debug."

... yeah, I'm still waiting.

nostromo123 commented on Farmers' protest party win shock Dutch vote victory   bbc.com/news/world-europe... · Posted by u/version_five
peterashford · 2 years ago
False dilemma. People don't need dairy milk (a lot of the world is dairy intolerant anyway) and there are alternatives that don't pollute anywhere as much, don't need as much land nor water and which are inexpensive and getting cheaper all the time.
nostromo123 · 2 years ago
"A lot of the world is able to walk, so people don't need wheel chair access in buildings". "A lot of the world is male/female, so people don't need made up genders and surgery". ... sounds great, huh?

Anyway, where does this "people don't need X" stop, though? You also don't need oat milk, tofu, soy, peas, etc. to survive.

Let's just go back to foraging for roots and berries and see what population size we can sustain!

nostromo123 commented on Who Blew Up Nord Stream? Investigators Focus on 6 Mysterious Passengers on Yacht   wsj.com/articles/who-blew... · Posted by u/nradov
nostromo123 · 2 years ago
Absolutely agree! Well, they had to scramble to spin up something fast, it's the best they could do.
nostromo123 commented on Women Are 41% More Likely to Experience Toxic Workplace Culture Than Men   sloanreview.mit.edu/artic... · Posted by u/qwerty242586
19h · 2 years ago
I agree this probably shouldn't be here, but I took all comments from this thread and asked GPT4 to 1) break down all arguments into axioms and 2) try to resolve them. Since I feel like this is pretty fascinating and a good read, I decided to paste this here.

Here's the reply:

------

In the discussion, various arguments have been presented surrounding the claim that women are 41% more likely to experience toxic workplace culture than men. Here, we break down the arguments into axioms and attempt to resolve them.

Argument 1: The data only shows that women are more likely to report toxic workplaces.

Axiom 1A: Women are more likely to report toxic workplaces than men.

Axiom 1B: Men are less likely to report toxic workplaces, possibly because they don't want to be perceived as a liability.

Argument 2: People typically report toxic workplaces when they are indeed toxic.

Axiom 2A: If a workplace is reported as toxic, it is likely actually toxic.

Argument 3: Men might react differently to toxic workplaces.

Axiom 3A: Men may take direct action against a former employer rather than report them on Glassdoor.

Argument 4: Women can also create toxic work environments.

Axiom 4A: Women can engage in aggressive and indirect behavior towards each other.

Axiom 4B: Evolutionary instincts and competition for resources, attention, and prestige might drive this behavior.

Argument 5: Cultural expectations shape how men and women respond to negative experiences.

Axiom 5A: Men are culturally expected to internalize negative experiences.

Axiom 5B: Women are culturally expected to attribute negative experiences to external factors.

To resolve these arguments, one could consider the following points:

1. Acknowledge that the data may reflect both actual toxic workplace experiences and differences in reporting rates between men and women. This would account for Axioms 1A, 1B, and 2A.

2. Recognize that both men and women can contribute to toxic work environments, as illustrated by Axioms 4A and 4B, but also acknowledge that they may respond differently to these experiences (Axioms 3A, 5A, and 5B).

3. Encourage open dialogue about toxic workplace culture, focusing on the experiences of both men and women, while considering the various factors that might influence their behavior and responses.

4. Promote research that investigates the different factors that contribute to toxic workplace culture, including individual, social, and cultural factors, as well as potential biases in the reporting of toxic workplaces.

By addressing these points, it is possible to gain a more comprehensive understanding of toxic workplace culture and the various factors that contribute to the differences in reported experiences between men and women.

------

As a fun exercise I made it generate a graphviz digraph from it: https://dreampuf.github.io/GraphvizOnline/#digraph%20Toxic_W... (prompt: Write a graphviz digraph based on your previous response.)

nostromo123 · 2 years ago
"I agree this probably shouldn't be here..."

And yet, here it is ;) This whole "asked GPT, here's what it said" spiel is getting old already.

nostromo123 commented on Will AIs take all our jobs and end human history? It’s complicated   writings.stephenwolfram.c... · Posted by u/kawera
still_grokking · 2 years ago
> Experts in the fields have been predicting that since the invention of computers, so we're closing in on 100 years of "trust me bro it's just around the corner"

Even that's true, simple extrapolations on raw computing power make the 15 - 25 year estimate realistic. That was definitely not the case 100 years ago.

> AGI won't build a house

Are you sure? Computers are already a indispensable tool when it comes to planing something like a building. Without computers the planing would be much more labor intensive and much less safe.

And when it comes to the physical building: The branch of robotics for application on construction sides is more or less exploding the last few years. It won't take long and a lot of work on a building site can be almost fully automated.

> AGI won't pick up your trash

Well, actually cleaning robots are the first "serous AI powered robots" that start to show up in more and more average households. And even "simple" vacuum cleaner robots need quite some AI…

So AI way below AGI is already picking up the trash; and that's just the beginning.

> AGI won't mine your lithium, &c.

It won't? I'm not sure.

AI helps already to find new mining sites.

Also like with construction sites mining is something that gets automated more and more with every year passing.

All the dangerous and labor intensive but profitable tasks get automated first. That's a clear trend throughout history.

I myself am very skeptical on the current AI hype. Though I'm very sure our AI Overlords are coming, and this will happen sooner as some people would like. In 25 years we will have enough processing power to simulate human brains just by brute force. That's more or less a given. But maybe so much computing power isn't even required to reach AGI—if the used software is constructed in a smart way.

nostromo123 · 2 years ago
Forget AGI, just make a robot that can fold laundry. I'll be here waiting :)
nostromo123 commented on Chat GPT4: Is the world prepared for the coming AI storm?   bbc.co.uk/news/world-us-c... · Posted by u/open-source-ux
lordnacho · 2 years ago
Eh, I'm not someone who is easily impressed, but I'm going to say LLMs are transformative (ba-dum-dum-sheeeesh).

I use copilot, it definitely saves me time. At the moment just minor things, but there's no arguing, there's simply no doubt.

ChatGPT will transform forum comments. Soon human written messages like this one will be swamped by machine-assisted argue-bots. And sales-bots.

Other LLMs are doing images, which will be much the same. You can illustrate your book automatically, pretty much now. You can generate marketing images, now.

Everything creative will be affected. Music, books, movies.

nostromo123 · 2 years ago
Then I guess I can ethically pirate anything I want, since I'm not "stealing the money from a human creator" anymore, huh?

u/nostromo123

KarmaCake day62September 30, 2016View Original