Skip to main content

Search

Items tagged with: ChatGPT

A study asked 50 doctors to make six different diagnoses for medical conditions. "Doctors who did the project without AI got an average score of 74%, doctors who used AI got an average score of 76%, and ChatGPT itself got an average score of 90%." "AI didn’t help doctors using it as much as anticipated because physicians “didn’t listen to AI when AI told them things they didn’t agree. Most doctors couldn’t be convinced a chatbot knew more than them." #LLM #AI #ChatGPT qz.com/chatgpt-beat-doctors-at…

ChatGPT beat doctors at diagnosing medical conditions, study says

The small study showed AI outperforming doctors by 16 percentage points
Ben Kesslen (Quartz)
#AI #llm #chatgpt

Unpopular opinion from a desktop apps fan: why does anybody need a #ChatGPT desktop app if it's just, well, website wrapped in a Windows executable?
#chatgpt

Alt space to call up an app any time? Great. Who needs the system menu anyway? Seems like idiocy to me but what do I know? #ChatGPT
#chatgpt

Also about excessive European regulations. It seems to be the reason why #ChatGPT advance voice chat doesn't work in the EU.
#chatgpt

😲 Kyle Kabasares, a Physics PhD graduate working at NASA's Ames Research Center, gave the methods section of his research paper to ChatGPT O1 Preview and asked it to generate the code based on the description. After just six prompts, it produced a working version of the code that took him a year to develop during his PhD. #ChatGPT #LLM #ML #AI youtube.com/watch?v=M9YOO7N5jF…
#AI #ML #llm #chatgpt

This Canadian Member of Parliament asked ChatGPT for a list of capital gains tax rates by country, got a nonsense answer, screenshotted it, and then tweeted the incorrect information.

(He later deleted the tweet.)

#canada #cdnpoli #twitter #x #ai #chatgpt #misinformation

Ryan Williams @Ryan_r Williams Socialism often starts with simple promises. In Canada, we’re seeing how increased capital gains tax rates, June 25 at 66.7%, can impact everyday Canadians. Let’s ensure we have common sense economic policies promote growth and bring it home! (CHATGPT Screenshot): Here is the list of capital gains tax rates for the G7 nations, including average provincial or state rates, along with the country flags: 1. Canada: 66.7% 2. France: 34% 3. Germany: 26.38% 4. ltaly: 26% 5. Japan: 20.315% 6. United Kingdom: 20% 7. = United States: 23.8% ...
#AI #twitter #canada #misinformation #cdnpoli #chatgpt #x

Dnešný fail ruzzkého trolla bol tak rozkošný, že som sa trošku rozpísal - takže kŕmiť či nekŕmiť trollov?

herrman.sk/home/krmit-ci-nekrm…

#troll #chatgpt #llm #fail #blog

Kŕmiť, či nekŕmiť trollov? | Ľuboš Moščovič o bezpečnosti

Informačná bezpečnosť sa týka každého!
www.herrman.sk

  • Kŕmiť (0 votes)
  • Nekŕmiť (0 votes)
  • trollololooooo (0 votes)
Poll end: 5 months ago

#blog #fail #troll #llm #chatgpt

Houston we have a problem... #captcha #chatgpt
ChatGPT solving a captcha
#captcha #chatgpt

Good. Biden's appointment of Altman to the AI safety and security board is up there with his Garland and Fauci appointments. Bad decisions.

The man has been accused by those who know him in his own inner circle of being "not consistently candid" and if there's anyone who should not be deciding AI risk issues it's someone not candid.

"Scarlett Johansson scandal puts OpenAI's Sam Altman back in the hot seat"

axios.com/2024/05/22/altman-op…

#AI #OpenAI #ScarlettJohansson #SamAltman #ChatGPT #Sky

#AI #openai #chatgpt #sky #scarlettjohansson #samaltman

Sh*tf*ck 😳🔥😔

#ChatGPT consumes 25 times more #energy than #Google

"Energy consumption by Artificial Intelligence (#AI) is rising rapidly: AI is predicted to consume twice as much energy as the whole of France by 2030, according to some calculations."
brusselstimes.com/world-all-ne…


ChatGPT consumes 25 times more energy than Google

"The negative impact of AI needs to be mitigated. Business leaders should be aware of the growing environmental impact of AI and take action."
www.brusselstimes.com
#google #AI #energy #chatgpt

Europäische Datenschützer reichen Beschwerde gegen OpenAI ein

Das KI-Programm ChatGPT veröffentlicht Daten über Privatpersonen, deren Herkunft unklar sei. Das werfen Datenschützer dem Anbieter OpenAI vor. Zudem ließen sich falsche Angaben nicht korrigieren.

➡️ tagesschau.de/wirtschaft/verbr…

#Datenschutz #DSGVO #ChatGPT #OpenAI #Noyb


Europäische Datenschützer reichen Beschwerde gegen OpenAI ein

tagesschau.de
#datenschutz #DSGVO #noyb #openai #chatgpt

How to (try to) block #IA scrapers with a tailored `robots.txt`:

You may want to use:
[Dark Visitor](darkvisitors.com/)

And:

[ai.robots.txt](github.com/ai-robots-txt/ai.ro…)

Adding to the list the `robots.txt` by #VLC:

[VLC robots.txt](videolan.org/robots.txt)

Source: **Bloquer les gaveurs d'IA** by @lord (in French)

lord.re/fast-posts/76-bloquer-…

#ChatGPT #IA #Robots #Scraper

Bloquer les gaveurs d'IA

Vous avez un joli site ouaib avec vorte ptit contenu écrit main. C'est votre blog, votre espace de réflexion, votre zone de création, votre espace rien qu'à vous partagé au monde, votre rejeton… C'est super chouette mais bon maintenant en 2024, ça ve…
/home/lord
#VLC #chatgpt #ia #robots #scraper @Lord

On Tech Talk this week, I had a great conversation with Troy Otilio from @AiraVI about their new Access AI feature, which has recently been released as a beta in the Aira Explorer app. We spoke about where this feature came from, the impact the use of AI has on privacy, and so much more about AI and Aira in general. Have a listen here or wherever you get your podcasts

podcasts.apple.com/gb/podcast/…

@rnib #aira #AccessAI #AI #chatGPT #gemini #blind #accessibility #podcast


‎RNIB Tech Talk: Tech Talk 508: Access AI, WelcoMe In Currys, RNIB Gamer Survey on Apple Podcasts

‎Show RNIB Tech Talk, Ep Tech Talk 508: Access AI, WelcoMe In Currys, RNIB Gamer Survey - 16 Apr 2024
Apple Podcasts
#Accessibility #gemini #blind #podcast #AI #chatgpt #aira #accessai @RNIB @Aira

#AI is used for more than just #ChatGPT 🤖

Algorithms analyze your behavior patterns & can monitor entire populations with little effort. 🔎

We need strong legislation to protect against expansion of the #surveillance state! 🚫🕵️‍♀️

👉 forbes.com/sites/forbestechcou…

AI is making it easier for intelligence agencies and law enforcement to monitor your every move.

Artificial Intelligence: The New Eyes Of Surveillance

While artificial intelligence systems continue to be hyped in 2024, the risks posed to data privacy can no longer be ignored.
Matthias Pfau (Forbes)
#AI #surveillance #chatgpt

No alkohol yet, but the first spontanuous singing is already done. Oh it smellsgood, oh it smells fine. I guess #ChatGPT is able to give full description. 😃 #MushroomFM

#mushroomfm #chatgpt

Lehce nekorektní školení...
Brainfuck pro opilé zedníky. 🤭

#brainfuck #chatgpt #openai

#openai #chatgpt #brainfuck

OpenAI si vsimlo o jake niche je zajem v tisicich AI startupech a spustilo vlastni "GPT builder".

Je to celkem dobra evoluce v pouzitelnosti. Dost lidi si najde vlastni pouziti ChatGPT a to se pro ne stane synonymem pro AI. Napriklad doplnovani kodu, analyza tabulek, zkracovani textu, copy na socky... Pojmenovane chaty s jakoby ruznou funkci jim tuhle kotvu pomuzou zvednout.

Tech vsech AI startupu mi vubec neni lito.

*obrazek vygenerovan random z Cosmic Dream GPT modulu.

#ai #chatgpt

Strom na mesici. Vygenerovano GPT modulem Cosmic Dream od OpenAI jako ilustracni obrazek.
#AI #chatgpt

OK, trying an experiment with my Programming Languages class!

• Have an AI generate some of your writing assignment.
• Critique its output. Call BS on its BS.

Assignment details in screenshots below. I’ll let you know how it goes.

(Here are the links from the screenshots:)

Raw AI Text:
gist.github.com/pcantrell/7b68…

Comments on AI Text:
gist.github.com/pcantrell/d51b…

(Better) Human Text
gist.github.com/pcantrell/f363…

#ai #chatgpt #education #writing #highered
#swift #proglang

Project check-in 2: Shred the AI Due Friday by 6pm I asked the ChatGPT AI to explain the core concept behind our Swift optionals activity. The AI produced an answer that was very impressive…for an AI. For a human, the answer would be pretty bad writing: fastidiously grammatical but verbose, full of fluff and waste, repeating ideas instead of synthesizing them, and sometimes just flat-out wrong. Here is what the AI wrote Links to an external site.. Here are my comments on its response Links to an external site.. (Don’t worry: I won’t be this detailed or this harsh with your writing. I want to be as critical as I can be, and I know I won’t hurt the AI’s feelings.) Here is my own attempt at a better answer to the same questions Links to an external site.. The fundamental problem with the AI’s answer is that it doesn’t really know what its main point is. It meanders around the relevant concepts, but it never quite manages to get to the heart of the central idea at hand. It is parroting fragments of the words of others, hoping that somehow they will coalesce into a coherent new thought. (They don’t.) It’s uncanny how much it’s like bad student writing. If I didn’t know this was written by an AI, I would probably think it was written by a student (or maybe an employee at a web content farm) trying to fill out their minimum word count at the last minute based on nothing but hasty web searching.
You all can do much better than the AI! Instead of doing a traditional pre-submission project check-in, I have a challenge for you: ask an AI to write a few paragraphs of your paper, and then critique its output. Here’s what to do: Use an AI (ChatGPT or other) to generate a few paragraphs of your final project. You can use the AI to generate English text or code, whichever is appropriate to your project. You can use ChatGPT or a different AI. The OpenAI account you need for ChatGPT is cheap but not free, and maybe a little intrusive. If you don’t want to set up an account and generate text yourself, let me know your topic and I will happily generate some text for you. Just ask. Save the raw text the AI gave you. Write comments about the AI’s output, much like the ones I wrote above. You can write your comments inline like I did, or use the Comments / Suggested Edits features of Google Docs, or use the Review / Track Changes features of MS Word. Consider the following: What is correct, a good point? What is wrong? What is missing? (This is the hardest one.) What is useless, just filler language? You do not have to be as detailed as I was with the AI. Quick notes are fine! Please send me (1) the original AI text and (2) your comments.
You do not have to create the “better human version” like I did. Of course, doing so might help you write your paper. If you choose to do that, however, don’t let the AI decide your paper’s structure for you. It might give you some good ideas for things to talk about! It might point out some ideas and resources you hadn’t considered! But it might also mislead you into a line of argument that is wrong (as the AI did with my response above), or into a structure that doesn’t make sense. Don’t switch off your own good sense — not for a computer, and not for a human either. Not ever. JUST TO BE CLEAR: Using an AI to help write your assignment would be cheating in most circumstances. Don’t let the fact that we are doing this as an exercise confuse you about the ethics of coursework in general! If you think an AI would help you with an assignment, you need to ask your instructor. Hopefully you already know all that, but I do not want to leave any confusion about it.

Raw AI text.md

GitHub Gist: instantly share code, notes, and snippets.
Gist
#AI #education #writing #swift #chatgpt #highered #proglang

My favorite outcome so far: a student remarked (paraphrasing here) that she didn’t realize how much she had to say in her paper until she saw how wrong the AI was, how much it missed the point.

Observing her own reaction to BS about her topic made her realize she’d underestimated the extent of her own newly-forming knowledge. That…that is the sort of outcome an educator dreams of.

#ai #chatgpt #education #writing #highered

#AI #education #writing #chatgpt #highered

Interesting #ChatGPT prompting technique!
1. Telling #AI model to “take a deep breath” causes math scores to soar in study!
2. #OpenAI DALL-E pays more attention to words in all caps.
3. Don't forget to say thank you and please to #LLM because Simon Willison thinks "in the training data, there are lots of examples where a polite conversation was more constructive and useful than an impolite conversation."
arstechnica.com/information-te…

Thanks to AI, the future of programming may involve YELLING IN ALL CAPS

Politeness and emphasis play a surprising role in AI-model communications.
Ars Technica
#AI #llm #openai #chatgpt

ONLYOFFICE 7.4 Adds Draw Tools and Plugin Support for ChatGPT omgubuntu.co.uk/2023/06/onlyof… #opensource #ChatGPT
screenshot showing how ChatGPT integration looks in ONLYOFFICE 7.4

ONLYOFFICE 7.4 Adds Draw Tools and Plugin Support for ChatGPT

Some neat improvements feature in the latest update to ONLYOFFICE, an open-source productivity suite for Windows, macOS, and Linux. As always I’m not shouting the name to annoy you, it’...
Joey Sneddon (OMG! Ubuntu!)
#opensource #chatgpt

@BorrisInABox this is something I put together for #TowelDay using #ChatGPT and the voice of Douglas Adams. I tried it with Peter Jones but that means a lot more work to get the inflections where I wanted them.

#chatgpt #towelday @Patrick Perdue

This is the funniest thing I've seen in a while. Someone asks #ChatGPT to rewrite a simple statement (sitting outdoors enjoying a bagel) in a way that cannot possibly cause any offense to anyone.
In the spirit of celebrating diverse perspectives, I'd like to share an experience from my personal life. It's a beautiful morning here, characterized by fair weather and the invigorating light of the sun, acknowledging that local weather conditions may vary greatly worldwide. I'm currently engaging in a personal breakfast routine that involves consuming a type of baked bread product known as a bagel, a food choice that | recognize may not resonate with everyone due to differing tastes, cultural practices, dietary restrictions, or health considerations. This particular bagel is topped with cream cheese, again a personal preference and not a universally endorsed one, considering various dietary preferences or restrictions, including lactose intolerance, veganism, and more. | am also appreciating this meal in my personal outdoor space known as the backyard, which | understand is a privilege not available to all due to diverse living conditions and economic circumstances. This message does not aim to disregard or belittle any individual's differing experiences, but rather to communicate a moment of personal enjoyment and satisfaction.
#chatgpt

"Don’t Tell #ChatGPT Anything You Wouldn’t Want to See on a #Billboard"

"Here’s a simple tip: DO NOT use #AI on any work-related project without checking your company’s policy. Even if your company has no policy, think twice, or even three times, before you put anything work-related into an AI.
You don’t want to become infamous for triggering the privacy fiasco that spurs your company into creating such a policy."

uk.pcmag.com/ai/146847/dont-te…


Don’t Tell ChatGPT Anything You Wouldn’t Want to See on a Billboard

Chatting with an AI program feels personal and conversational, but don’t be fooled. Here's why you should keep a lid on what you reveal to ChatGPT and its ilk.
Neil J. Rubenking (PCMag UK)
#AI #chatgpt #billboard

Don’t Tell #ChatGPT Anything You Wouldn’t Want to See on a Billboard
pcmag.com/news/dont-tell-chatg…

Don’t Tell ChatGPT Anything You Wouldn’t Want to See on a Billboard

Chatting with an AI program feels personal and conversational, but don’t be fooled. Here's why you should keep a lid on what you reveal to ChatGPT and its ilk.
Neil J. Rubenking (PCMag)
#chatgpt

Before you install the new #ChatGPT app on iOS, ask yourself: what's the worst thing the maker of the world's greatest bullshit machine could do with this kind of information, and why are they requesting it?
App privacy settings for ChatGPT app, requesting a boatload of personally identifiable information
#chatgpt

I had #ChatGPT write a story for a friend of mine who just went through a colonoscopy and it seemed fitting to have it in the style of a Scotsman, although #ElevenLabs didn't change my accent to compensate. Still, it amuses me none the less.

#chatgpt #elevenlabs

Are AI tools really as smart as creative writers? 🧐 It looks like we will soon know for sure. In any case, AI and its influence on our societies must be watched closely: After all the tools were trained with human writers content who they are now supposed to replace.
vice.com/en/article/pkap3m/gpt…

Read more on this issue and why ChatGPT is a privacy nightmare: 👉 tutanota.com/blog/posts/chatgp…

#ai #creative #content #writers #privacy #chatgpt #bard #ernie


GPT-4 Can’t Replace Striking TV Writers, But Studios Are Going to Try

The desire to replace writers with AI is a symptom of the larger problem that the guild is fighting for—which is that companies do not value writers and their work. 
Chloe Xiang (VICE)
#privacy #AI #writers #chatgpt #creative #content #bard #ernie

For those not happy with #ChatGPT, maybe try this instead: huggingface.co/chat/

HuggingChat

The first open source alternative to ChatGPT. 💪
huggingface.co
#chatgpt

Sing it louder now: orgs offering #ChatGPT et al need to equip the prompt with full subject access rights support per the #GDPR nytimes.com/2023/03/31/technol…

ChatGPT Faces Ban in Italy Over Privacy Concerns

The action by Italy’s data protection agency is the first known instance of the chatbot being blocked by a Western country.
Adam Satariano (The New York Times)
#gdpr #chatgpt

I Out of sheer boredom and curiosity, I asked #ChatGPT to write a little essay about #TrafficLights and how they differ from country-to-country. I then had an #AI version of yours truly read it, courtesy of #ElevenLabs, so here it is. I even learnt a few things I didn't know, assuming of course, that Chat GPT is correct in what it wrote.

#AI #chatgpt #elevenlabs #trafficlights

#LAION (non-profit association from Hamburg, Germany) is working on an #OpenSource alternative to #ChatGPT. They are crowd-sourcing a conversation dataset to fine-tune an existing open source #LLM similar to how ChatGPT was created.

You can help creating the dataset on open-assistant.io!

The first dataset release is planned for 15. April 2023.

youtube.com/watch?v=64Izfm24FK…


OpenAssistant - ChatGPT's Open Alternative (We need your help!)

#openassistant #chatgpt #ai Help us collect data for OpenAssistant, the largest and most open alternative to ChatGPT.https://open-assistant.ioOUTLINE:0:00 - ...
YouTube
#opensource #llm #chatgpt #LAION

ChatGPT has leaked conversations and payment info of some users. While #OpenAI feels "awful" about this, experts say users "should have had zero expectation of privacy when using the #ChatGPT web demo."

theregister.com/2023/03/23/ope…

Read also our blog post on ChatGPT: A #privacy nightmare or a helpful tool? tutanota.com/blog/posts/chatgp…


OpenAI CEO 'feels awful' after ChatGPT leaks conversations, payment info

Delayed mea culpa isn't a good look for a biz with 'open' in the name
Jessica Lyons Hardcastle (The Register)
#privacy #openai #chatgpt

Not that bad… #ChatGPT
#chatgpt

Wow! Here's my variant: "Write a story about an intelligent AI assistant learning to speak to dogs. Write it in the style of Arthur C. Clarke." Voiced by #ElevenLabs Adam. #ChatGPT

#chatgpt #elevenlabs

Write a story about an intelligent AI assistant learning to speak to dogs. Write it in beautiful, flowery prose. Include exciting and dramatic sentences. #ChatGPT #ElevenLabs

#chatgpt #elevenlabs

Reading about #ChatGPT plug-ins and wondering why this is framed as plug-ins for #ChatGPT (giving it "capabilities") rather than #ChatGPT as a plug-in to provide a conversational front-end to other services.

Nevermind, I know why: This is #OpenAI yet again trying to sell their text synthesis machine as "an AI".

#MathyMath #AIHype

Screencap: "Though not a perfect analogy, plugins can be “eyes and ears” for language models, giving them access to information that is too recent, too personal, or too specific to be included in the training data. In response to a user’s explicit request, plugins can also enable language models to perform safe, constrained actions on their behalf, increasing the usefulness of the system overall." Source: https://openai.com/blog/chatgpt-plugins
#openai #chatgpt #AIhype #mathymath

For my latest story, I got to correspond with a Ukranian developer with cerebral palsy who uses ChatGPT and GitHub Copilot to communicate and code. It was wild, because I don't think our interaction would have been possible just a few years ago.

Beyond that, though, #GenerativeAI is removing barriers for him to code and contribute. He even released his first #OpenSource project recently sharing his experience!

github.com/readme/featured/ope…

#ChatGPT #GitHubCopilot #GitHub #A11y

"From gaming with your eyes to coding with AI: new frontiers for accessibility" The image also shows a man with headphones on sitting on a giant hand, using the touch screen on a giant smartphone held by another giant hand.

From gaming with your eyes to coding with AI: New frontiers for accessibility

Open source offers developers with disabilities the flexibility needed to participate and collaborate. Their contributions and involvement in the research, design, and development of software are i...
Mike Melanson (GitHub)
#a11y #opensource #github #chatgpt #generativeAI #githubcopilot

⇧