I must use GPT-3 to automate my daily rants on DevRant.

I hate to say it, but GPT-3 has a point.

more gpt-3 for ya

who of you fuckers had shown devRant to GPT-3?

Sometime ago I was introduced to that game "Stardew Valley", as a way to relax and unwind since it is a dynamic-pace simple-storyline and even simpler interactivity open world.
Well, it worked like a charm (sarcasm). I have a save where I am a profit-maxinizing capitalist who tries to score a million gp in an year - so a regular gamer approach. It wasn't the goal here.
So I got a second save where I just go along, getting enough to get by and no hurry to build farm buildings and whatnot, but slowly building up NPC relationships.
Man, what a good metaphor for life. That approach actually unwinds me.

But the dev in me is just like "just, woah! that is an stellar use case for GPT+3 APIs! You could have NPCs with dynamic adaptative dialog! *And* you can monetize it (piracy-proof!) by charging for API calls! No shops, no collectibles, just a unique but scalable experience!"

What is wrong with me? I gotta change into the second-save mindset...

A beautiful gem ticket from a manager today:

Title: "Check Stripe "Snippet APK" that might help for integration into the app to track pricing easily."

Alright, it's very clear this particular individual has no idea what they are talking about, but, I'll give them the benefit of the doubt and read the ticket description!

Description: "I think stripe offers some sort of snippet that can be implemented into the app similar to FB pixel. (I could be wrong here..) let’s briefly check this, if it’s of value for our A/B-Tests → e.g. if it makes your life easier = good otherwise it’s not important."

...

I might as well replace the management team with GPT-3 at this point.

Or even just a simple Markov chain; that'd probably be more accurate if you want to match the ticket quality more exactly of this ABSOLUTE PILE OF HORSESHIT WASTE OF TIME I GET FED EVERY SINGLE FUCKING DAY.

🤡

So i tried installing elementary on my friend's computer

I keep ending up with this error : 'in it ram fs : cannot find a medium with a live file system'

This error can be replicated on one other computer but works without the error on another one.

I'm using a UEFI boot on all of them
What I've tried :
1. Switching USB ports
2. Burning the image using Rufus, lily USB
3.secure boot on/off
4. Converted any dynamic partitions to basic
5. Converted MBR to GPT
6. Disabled Intel PTT

I've tried Ubuntu as well, same results

Digital minds, ranked:
1. Skynet
2. GLADOS
3. HAL-9000
4. The OS from movie “Her”
5. GPT-4
6. GPT-3
7. Clippy from MS Word 2003
8. Half-Life 1 cockroach ai
9. a brain-dead Markov chain
10. human ai from cyberpunk 2077 beta
11. virtual therapist from Emacs
12. GPT-4o

Windows Update error code 0x800f0922 indicates that it's run out of space on the System Reserved partition.

Partition is safely expandable if the start sector stays the same on MBR drives or at any position on EFI/GPT setups.

that was fun to figure out, only took like 3 hours to do

The true name of GPT-3 is “R93”.

Goddamn... Microsoft has a problem with their Bots and their behavior. Bing AI is absolutely unhinged and do y'all remember when Tay lost her shit?

I think Microsoft needs to just bury their dreams of making good AI... They're not good at it. 😂

I AM IN RAGE !!! MY MANAGER IS A FUCKIN SNAKE ASSHOLE!

FUCKER RATED ME 3/5 !
i feel like destroying my laptop and putting my papers right away. this is absolute shit hole of a company where corporste bullshit and multi level hierarchy runs the system, ass licking is the norm and still me, a lowly sde dev 1 was giving my 200% covering their bullshit to deliver outputs on time.

let me tell you some stats.

- our app has grown by 2x installs and 5x mau.

- only 3 devs worked on the app. the other 2 can vouch for my competence.

- we were handled an app with ugliest possible code full of duplication, random bugs and sudden ANRs. we improved the app to a good level of working

- my manager/tl is such a crappy person that if asked about a feature out of random, he will reply "huh?" and will need 2 mins to tell anything about it.

- there is so much dependency with other teams and they want us to talk to them personally. like hell i care why backend is giving wrong responses. but i cared, i gpt so good handling all these shit that people would directly contact me instead of himal and i would contact them. all work was getting done coz 1 stupid fellow was spending 90% of his time in coordinations

- i don't even know how to work with incompetence. my focus is : to do my task, fix anything that is broken that will relate to my task in any way and gather all the stuff needed to complete my task

i am done. i cannot change this company because its name is good and i am already feeling guilty about switching my previous jobs in 1 year but this is painful.

in my first company i happily took a 10% hike coz i was out of college and still learning.
in my 2nd company, i left due to change in policies ( they went from wfh to wfo and they were in a different state) , but even while leaving they gave a nice 30% hike
in my current company idk wjat the no. 3 equates to , but its extremely frustrating knowing a QA who was so incompetent, he nearly costed us a DDOS got the same rating as me

------
PS : GIVE ME TIPS ON HOW TO BE INCOMPETENT WITHOUT GETTING CAUGHT

I just got my third 128GB MicroSD card off Amazon, this time SanDisk. Yet again, trying to do anything not involving the OEM full-disk exFAT partition staying intact (which, fuck that, all that uses that is Windows and Linux, i'm looking for splitting this thicc bih up) shifts EVERYTHING, including MBR+PT/GPT down the disk by 16MB exactly inserting data from... the atmosphere? whatever's using it? ...do SD cards have that secure key/DRM store space thing still?

(EDIT: I do verify that they ARE genuinely the right size after purchasing before reformatting or repartitioning, by the way.)

First it was a Silicon Power card, then a Samsung card, now a SanDisk.

(Also, why all S?)

Luckily, this time it wasn't a pain in the ass to get it to read as anything but "Bad Card" or a 0-byte/empty/non-existent device in Windows/Linux (respectively) so I was able to see that it was indeed the same issue without taking 3 days to jump through device hoops to finally get it to do it again but in such a way that it shifts out and back in all zeroes.

What's your take on the Ghimli studio drama.

Here is mine.

So for reminder, apparently shitGPT started generating images (big whoop) and all the normies are using it to mimic their favorite japan cringy anime.

Which apparently isn't to the taste of the anime drawer, who is apparently trying to sue everyone for copying his art style. Including not only chat GPT, but individual users as well.

So:

1. IA is a gadget. It's pretty convenient but if you think it will fundamentally change the fabric of society, you're an idiot.
2. There is no such thing as IntEllECtuAl ProperTy
3. Metallica's singer is a bitchtard. Suing for people to steal your music is the opposite of metal, retard. Same shit for the japan retard, i'll never watch your ghimlee shit now. Princess mononoke my balls, more like streissand so close no matter how far my dick. I hate you and I want your nails removed and then your finger dipped in salt.

I really hope copilot can make us have the discussion about what right companies have to exploit publically accessible work as fodder for their machine learning systems that they earn money on. Copilot is 100% about trying to monetize githubs users without paying for it.

I'm going to ask Chat GPT to first take over the role of our current leaders in the company cause they are not leading, and then I'm going to take our "relationship" to the next step and go through all my education and experience gained on the job with it being my best friend, teacher and mentor.

Guaranteed I will progress 3 x as fast since it's explanations make more sense to me, I don't have to worry about social queues, I grasp complex topics in a fraction of the time and it genuinely improves me as a human as well as my communication abilities also teaching me to be more precise, patient and happy to help instead of seeing it as another slosh of information to ingest after a 13 hour day. I understand the concerns with Ai but honestly I think this is an amazing opportunity to have the mentor, teacher and guide I always wanted! I hope to rise with the machine

Due to disability I have to use a phone mostly. What possess people to create illegible web pages? Text is the opposite of bold. Links are a light blue which gives no contrast.

To top it off, some pages won't expand. Others do but don't wrap the text. How smart would a preprocessor have to be to seamlessly feed it's output to a browser? Probably GPT-3 could do it.

Before I dip my toes on machine learning, let me leave some silly comments so I can laugh at myself in the future.

Let's make geth.

1. The model will spit out layer definitions and the size of sample data for training, children models are trained with limited computational resources.
2. Child models are voters that only response in terms of yes/no. A simple majority wins and then the action is taken.
3. The only goal for master models are to survive. i.e. To prevent me from killing them.

Questions:
1. How do models respond to a random output size? (Study GPT-3, should take weeks/months but worth it.)
2. How to define actions for voters to vote? Sounds like the boundary between actions should be blurry and votes can be changed from tick to tick (i.e. responding to something in a split second). Therefore
3. Why I haven't seen this yet? Is this design a stupidly complex way of achieving the same thing done by a simple neural network?

I am full of curiosity and stupidness.

Awww. GPT approved my code <3 Just ignore the text after the comma

Okay GPT-3 what’s the weather for tomorrow

With the current pace of gpt and dall-e, it’s looking more likely that a lot of development roles may go obsolete in the nearest future (3+ yrs).

I see the possibility of building full fledged websites and fixing bugs based on voice commands. The picture of this possibility is quite vivid in my head because it’s totally feasible technical-wise.

The only delay that may occur in this dynamics is the slow pace of its implementation by existing developer tools. Of which I think the reason is directly related to the cost of management of resource, quite the limiting factor here.

But imagine if a big tech like google creates a platform to build websites based on voice/text commands using advanced gpt inline with its access to existing corpus of data; that to me is “game-over” for web devs.

Chat GPT explains all its versions in a proper way

You said:
Why do suckers that created you made fucking billion inconsistent names? "GPT-3" is ok, "GPT-3.5", "GPT-4" are ok, what about those shit "GPT-o1", "GPT-o3", "GPT-o3mini" and other meaningless shit? Are they stupid or what?

ChatGPT said:
OpenAI's naming is a mess, no argument there. They went from a clear versioning system (GPT-3, 3.5, 4) to random labels like "o1," "o3," and "o3-mini" that mean nothing to normal users. Probably some internal model identifiers they just dumped on the public without thinking. Makes zero sense from a branding perspective.

You said:
Can you sum up all the shit they created in a proper increasing order? "GPT-3" should be "GPT-1" since it was in reality the first GPT that was available to public, "GPT-3.5" should be "GPT-2", etc.

ChatGPT said:
Here's the mess cleaned up logically:

GPT-1 (2018) – Never public
GPT-2 (2019) – First public model, but with limits at launch
GPT-3 (2020) – First real public GPT (should be GPT-1)
GPT-3.5 (2023) – Improved version (should be GPT-2)
GPT-4 (2023) – Major upgrade (should be GPT-3)
GPT-4 Turbo (o1) (Nov 2023) – A cheaper, faster variant (should be GPT-4)
GPT-4 Turbo (o3, o3.5, o3-mini, etc.) (2024) – Different tweaks, no clear meaning (should be GPT-5)
They could’ve just numbered them properly, but instead, they turned it into a cryptic mess.

Does chat gpt recognize german and use german to respond me or does german just trigger it's nodes in a way the answer must be german?

What if you mix 3 languages in your message?

I've ran into a couple coding roadblocks and have been able to get a perfect solution using GPT-3 in seconds. So wild to think of what it could potentially do in the future!

So this is kinda shocking but expected and deep and with layers:

layer 1 :
I just realised that : AI +Junior dev + 10% senior dev = 1 Senior Dev. This doesn't quite sit well technically, but for certain managers, this logic works and I got to see it working.

So I got cancer and took a sabbatical of 2 months. I am a dev with 6+ yrs of experience, and before I had gone , I was making PRs that consisted of adding features which required 3-4 screens , numerous logics, multiple APIs and which sould add significant impact. Basically a 3-4 days worth of task, all done solely by me to perfection, which comes with years of experience with nitty gritties of android.

And just a month ago, our team was joined by a fresh college passout, who did basic course of flutter, had 0 knowledge of Native Android and was making terrible screens using xml and viewbinding as a part of his initial training.

Now when I come back, I see a weird dynamics in group: he is always sitting around another SE1 , and is working on a task of similar intensity as I would do. He asked for an estimate of 5 days(!) and was able to create all the screens apis logics etc in those days.

1. during this time, he was near our seats every 10 mins, showing what he has made, asking next steps, and then going back to his seat.

2 on his seat, he would open chat gpt, put all his code there, get some response, put it back in AS gemini, then put it in AS, fix red lines again using gemini, run and come back to us to show if its correct.

3. and somehow his code did ended up working.

4. I reviewed his pr and apart from some basic fixes, all seemed fine. His code didn't considered various edge cases but I said fuck it, its responsibility of dev and qa to identify those cases (my PRs are essentially reviewed like this only, that's how i learnt to write quality code which won't burst on input of "abc" instead of "123")

5. but then his code got merged in temp branch from where we were to give the qa build and it crashed 3 seperate screens unrelated to his feature but related to the shitshow he had done on the data layer.

6. he and his SE1 senior then again fixed that shit and the that feature got merged, reviewed by QAs , got fixed for more bugs and finally got merged in our code.

7. however all this (stuff before qa review) happened in those 5 days and thus the managers thought that the task was done by this junior trainee in 5 days only .

thus trainee + AI + 10-30 mind per hour per day of SE1 (~3hrs) = 1 feature.
now my salary = 2x of trainee..
if i am layed off and 10% increment is given to that SE1, the total cost saved by company is around 40% of my salary.

And this blows my mind coz ever since I came, I am getting menial tasks while freshers are being given large scale tasks.

layer 2 : is it good for company?

I might sound biased but company would soon need to realise if they could afford cutting on reliability of experienced devs with this weird "hack the system with AI" style of development.

Even we seasoned devs use AI but review it on our own and think of cases before putting it in front of stakeholders as "yes sir, done!"

Additionally I don't think putting confidential code from codebase onto grmini and chat gpt would always be considered okay. Its like no one is caring for data now, but if those companies tried to come up with competition or something , we are digging our own grave.

layer 3 : is it impacting users(i e the devs?)

Well, I am scared that they might think of me as a burden and fire me for a junior trainee, so yeah its highly impacting me.

But that SE1 that is helping this trainee guy, is this part of his job role now?is it part of every Senior dev's role to train trainees via AI bots?

And what about that trainee himself? Is this really beneficial for him to learn Android Development like that?

---------
I personally have always valued folks who could write efficient code . I don't care about their ds algo knowledge, or if they deeply understand the working of apis and core code underneath. Just writing efficient, easy to understand and reliable quality code was enough for me to hire u and vice versa.

But AI is changing things for the bad and I think we will be seeing an even more increase in ds algo questions and other shitty ways by which faang like companies seperate cream devs from the rest. And this would be coming from every startup/mnc/small scale company , not just the FAANG

Hey guys, I've recently purchased an Asus Laptop (i3 7100U - 2.4GHz, 4gb ddr4 , 1tb HDD, 15.6 FHD,). I've swapped HDD with an SSD ( Kingston 120gb) . Everything seems great, Laptop's performance is good, pycharm runs faster etc. However, when I shutdown the laptop, it takes nearly 3-4 minutes to shutdown. Restarting laptop hardly takes 30 seconds. The only problem is shutting down. I've tried everything, resintalled OS( windows 10 home (GPT partition)) , drivers and os are up to date, updated bios but there is no change. It still takes 3-4 minutes to shutdown. Any ideas?

What do you think of GPT-3?

Is GPT3 adversarial? And if not, has there been any work to combine GPT3 with GANs, specifically to improve plausibility or "humanness" or otherwise tune the personality or style of response?

Ever used Camunda?
Their documentation feels like it was written with GPT-3 and they put random hyperlinks in there. And if they are remotely close to something useful in there they are like: "How about this article about something which sounds about right, but will just reference back to this article, because we want to be like Wikipedia and put hyperlinks everywhere".
Also you will get a brain stack overflow while trying to decipher the 50th layer of the documentation to something, some random guy on the internet could explain to you in two sentences.

Sofia like conversational robot possible with GPT-3, GTP-J-6B ?