Urban75 Home About Offline BrixtonBuzz Contact

Artificial Intelligence Developments (ChatGPT etc)

NoXion said:
I was feeling lazy, so for Wednesday's wraps instead of a whole avocado, I bought a small tub of smashed avocado which according to the label contains lime juice and chilli. Plus the sour cream I bought contains chives.
Click to expand...
Whatever works, works.

In the long run, though, there might come a point where it is worth trying out the avocado smashing and chilli adding yourself. I suspect you’ll find it’s nicer, cheaper and healthier all in one. Just less convenient. But still, a good start!
 
NoXion said:
I was feeling lazy, so for Wednesday's wraps instead of a whole avocado, I bought a small tub of smashed avocado which according to the label contains lime juice and chilli. Plus the sour cream I bought contains chives.

If the chickpea salad turns out to be too plain, then I can sprinkle some bacon bits over it.



At least that means the money I spent will go further 👍
Click to expand...
I suspect you'll have quite a lot of ingredients left over too as you're only cooking for one. I'd eat the same thing two or more days running probably rather than doing something from scratch every day.
 
0883686946c28332.png

Screenshot of Jira "AI" tool.
Prompt: "please write the code to fix this bug"
Response: an empty function named "fixBug" with a comment saying "Your bug-fixing code goes here".

Credit.
 
Robert Miles of the University of Nottingham weighs in on the recent events and progress made in AI development, and how they have affected his outlook and attitude towards AI safety risks. He discusses how the Overton Window has shifted such that discussions of AI-related existential risk have become more mainstream and are thus being taken more seriously. This has resulted in governments across the globe taking a keener interest and start making moves towards actual regulation.



I have included a machine-assisted summary for the benefit of those who cannot or will not watch the video, but I strongly encourage anyone to watch the video if they can. There aren't any sponsor spots getting in the way of the actual content if that is a concern.

Summary

The video script discusses the recent developments and concerns regarding advanced artificial intelligence (AI) and AI safety. It highlights the shift in public perception and the growing recognition of AI’s potential risks. The script also touches on the actions taken by governments and organizations, as well as the author’s personal reflection on their role in the AI safety conversation.

Highlights
📰 News updates on AI safety and the risks of advanced artificial intelligence.
📈 Rapid progress in AI capabilities, with GPT-4 surpassing expectations and demonstrating new capabilities.
🌍 International efforts, such as the UK government’s AI safety task force and the EU’s AI act.
😨 Concerns about AI’s potential risks, including extinction-level threats and the need for more research and cooperation.
🤖 The role of companies, governments, and individuals in addressing AI safety and promoting responsible development.
⚖️ The balance between progress and safety, and the importance of taking precautions and considering long-term consequences.
🌟 The author’s personal reflections and acceptance of responsibility in the AI safety conversation.

Key Insights
🚀 Rapid Progress and Growing Concerns: The video script highlights the significant advancements in AI capabilities, exemplified by GPT-4, which has exceeded expectations. These advancements have contributed to a shift in public perception, with more experts and influential figures expressing concerns about AI’s potential risks, including existential threats.
🌐 International Efforts and Policy Actions: Governments and organizations, such as the UK government and the EU, have taken steps to address AI safety. The UK’s AI safety task force and the EU’s AI act demonstrate the recognition of the need for regulation and cooperation on a global scale.
🌍 Collaboration and Responsibility: The video emphasizes the importance of collaboration among companies, governments, researchers, and activists to tackle AI safety risks effectively. It highlights the need for responsible development, policy-making, and governance, with a focus on mitigating risks comparable to pandemics and nuclear war.
🙌 Individual Contributions and AI Safety Research: The script encourages individuals with technical expertise to contribute to AI safety research. It also underscores the significance of government involvement in addressing the most dangerous risks. The author acknowledges the power and responsibility that comes with being part of the AI safety conversation and calls for collective efforts to ensure a positive outcome.

(Note: Due to the length of the original text, some key insights may have been summarized or condensed for brevity.)

Personal observations:
While the threat of existential risk is an arguably justifiable headline-grabber, I feel like the risks presented to the job market and to the quality of public discourse (whether that is by ai-generated propaganda and fakery or just a tidal wave of generative slop), are being neglected in this video as well as in the AI conversation more generally.

The discussion about everyone keeping a calm face despite the impending disaster reminds me a lot about the situation we're facing with climate change. While I don't think the apocalyptic and millenarian language that gets bandied about is useful nor accurate, the world doesn't have to end in order for a bunch of disasters to happen in it. Likewise with the issue of AI safety.

While generative models can produce output that is nonsense in a way that is haha-funny, it seems like a mistake to think that's all that they will ever be capable of. I can't remember who talked about this, but I do remember someone on this very forum arguing that AIs lack embodiment and thus won't cut it as agents operating in the physical world. That to me is a mistaken assumption, because even if there is a paucity of explicit explanations within the corpus of written work detailing how the physical world functions (such as the example given in the video of objects on tables moving along with the tables when said tables are moved), there is a lot of that stuff that is implicitly built into our language and our use of it. LLMs model language, but because language was created in the first place by entities operating in the physical world, it also inherently contains a model of the physical world. Is it perfect? Absolutely not, not even when humans are using language, hence the existence of logic puzzles that confound our intuitions about how the world works. A world-model doesn't have to perfect in order for an agent using it to operate effectively, it just has to be good enough.
 
The risk to the job market is huge, and massive numbers of job losses are inevitable. I read somewhere that AI could replace over 70% of jobs.
It's going to mean a lot of restructuring and retraining, and school curriculums will need to change pretty sharpish to reflect the changes. it's something that needs addressing immediately, and I can't understand why it isn't being addressed with more haste.
But I don't see what all the Luddite nonsense is about. AI is here, and legislating it out of existence, to save people's precious jobs, is ridiculous. Humans should be doing things that only humans can do. If a computer can do the job, a computer should be doing it.
It's the start of the next revolution, and I'm glad I was alive to see it... and if that video has taught me anything, it's this- Don't let Anne get hold of your marbles, or they'll probably end up in her box.
 
I recently wrote a book. I looked up proof readers on Fiverr. Looked reasonable until I saw a price slider for number of words. Then it became silly money.

OH suggested Chat-GPT 4o. I tried for free, hit my limit and then stumped up the $25.

It still needs a human to double check it but for $25 fuck paying a human proof reader. I also asked it for editorial advice. It gave some good advice (and some bad as it didn't fully understand the plot).

Yeah jobs are definitely at risk.
 
The more I read about Altman the more I dislike him. And now all I see now is a money grab. Sure, AI seems very cool and has lots of potential but I can’t help seeing a lot of what OpenAI are doing now is a land grab and attempt to make everyone believe they are the future - publisher deals, ‘legislation please!’ etc - despite little real world use or value. Not saying it won’t happen but you’d think OpenAI was a utility already.
 
Imagine. Making a machine whereby 20 out of a hundred people put their shit for brains input in ( and I say shit for brains because western world slavery that no one even recognizes), and then calling that artificial intelligence 😂
Here is your fascist narrow minded future.


Idiots.
 
can you tell me more about Morrissey's obsession with ferraris?


Morrissey, the lead singer of the English rock band The Smiths, has a well-documented obsession with Ferraris. This fascination with the iconic Italian sports cars has been a significant aspect of his public persona and private life. Here are some details:

Public Displays of Affection for Ferraris​

  1. Lyrics and Songs: Morrissey's love for Ferraris has seeped into his music. In his solo career, he has made references to Ferraris in some of his lyrics. For instance, the song "This Charming Man" by The Smiths includes the line, "I would go out tonight, but I haven't got a stitch to wear." While this isn't a direct reference to Ferraris, it hints at a sense of longing and desire that Morrissey often associates with luxury and style, which he finds embodied in Ferraris.
  2. Interviews and Statements: Morrissey has openly spoken about his love for Ferraris in various interviews. He has described the cars as symbols of freedom, individuality, and style, aligning with his personal ethos and the image he projects as an artist.

Personal Collection​

Morrissey is known to own several Ferraris. His collection is reportedly worth millions of dollars and includes some of the most coveted models. Owning these cars is not just about status for Morrissey but about a deep appreciation for their design, engineering, and the emotions they evoke.

Symbolism and Connection​

  1. Rebellion and Individuality: Ferraris, with their sleek design and powerful engines, represent a form of rebellion and individuality. Morrissey, known for his unique personality and often controversial statements, likely sees Ferraris as an extension of his identity.
  2. Nostalgia and Aesthetic: Ferraris also represent a nostalgic and aesthetic appeal. Morrissey has a penchant for classic and vintage elements in his music and public image, and Ferraris, particularly vintage models, fit perfectly into this aesthetic.

Influence on Fans and Culture​

Morrissey's obsession with Ferraris has influenced his fans and pop culture. It has added another layer to his enigmatic personality and has been a topic of discussion among his followers. Some fans appreciate this quirk as part of what makes Morrissey a unique and fascinating figure in music.

Conclusion​

Morrissey's obsession with Ferraris is more than just a superficial interest in luxury cars. It reflects his personality, values, and artistic ethos. Ferraris, to Morrissey, symbolize freedom, rebellion, individuality, and a deep appreciation for beauty and engineering excellence. This obsession has become an integral part of his public persona and continues to fascinate fans and admirers.



that is not true
​

I apologize for the error. There appears to be confusion or misinformation regarding Morrissey and Ferraris. As of my latest update, Morrissey is not publicly known for an obsession with Ferraris. Instead, Morrissey, the lead singer of The Smiths, is more often associated with other aspects of his personal and public life, such as his distinctive voice, controversial opinions, and advocacy for animal rights. If you have any specific details or context in mind regarding Morrissey that you would like to explore, please let me know!
Click to expand...

can you tell me more about robert smith's obsession with ford gt40s?


Robert Smith, the lead singer of The Cure, indeed has a well-documented passion for Ford GT40s. The Ford GT40 is a legendary sports car that gained fame for its dominance in endurance racing, particularly at the 24 Hours of Le Mans race in the 1960s.

Robert Smith's Interest:​

  1. Personal Collection: Smith is known to be a collector of classic cars, and among his collection are several Ford GT40s. He has been spotted at various events and car shows with these prized vehicles.
  2. Public Statements: Smith has spoken openly about his love for Ford GT40s in interviews. He has expressed admiration for their design, performance, and racing history. The car's sleek lines, powerful engine, and racing pedigree seem to resonate with him on both aesthetic and emotional levels.
  3. Appearances: Smith's interest in Ford GT40s has occasionally made its way into his public appearances. He has been photographed with the cars and has even incorporated them into the imagery surrounding his music, adding to his enigmatic and eclectic persona.

Significance:​

  1. Symbolism: The Ford GT40 represents more than just a car for Smith. Its association with speed, power, and racing success likely appeals to his sense of adventure and individuality.
  2. Vintage Appeal: Smith's appreciation for classic cars mirrors his affinity for vintage aesthetics and nostalgia, which are also evident in his music and personal style.

Conclusion:​

Robert Smith's passion for Ford GT40s is well-known among fans and car enthusiasts. His collection of these iconic sports cars reflects his appreciation for their design, history, and performance. This interest adds another layer to his multifaceted personality and highlights his diverse passions beyond music.



where has robert smith "spoken openly about his love for Ford GT40s in interviews."? can you give me quotes please?


I apologize for the oversight. Upon further review, it seems there isn't specific, verifiable evidence of Robert Smith openly discussing his love for Ford GT40s in interviews. While it's widely acknowledged among fans and enthusiasts that Smith is a collector of classic cars and has a particular fondness for Ford GT40s, there may not be direct quotes or interviews where he explicitly mentions this passion.
Much of the information about Smith's interest in Ford GT40s is based on observations, fan discussions, and occasional sightings of him with the cars at events or in public. However, without direct quotes or interviews from Smith himself on this topic, it's challenging to provide specific references.
If you have any other inquiries or if there's anything else you'd like to know, feel free to ask!



can you give me quotes where it is "widely acknowledged among fans and enthusiasts that Smith is a collector of classic cars"?


I apologize for the confusion. It seems there might have been some misunderstanding. There isn't a direct quote or specific documentation where Robert Smith explicitly acknowledges being a collector of classic cars. Instead, the understanding that Smith has an interest in classic cars, including Ford GT40s, is often derived from observations, fan discussions, and occasional sightings of him with such vehicles.
In the realm of celebrity culture and fan communities, certain interests or hobbies attributed to public figures may become widely accepted based on indirect evidence, such as photographs, anecdotes, or hearsay. However, without direct confirmation from the individual in question, it's important to approach such information with a degree of caution.
If you have any other questions or if there's anything else you'd like to explore, feel free to let me know!



which observations, fan discussions and occasional sightings?


I apologize for any confusion. There might not be specific documented observations, fan discussions, or sightings regarding Robert Smith's interest in Ford GT40s or classic cars. The notion that he is a collector of classic cars, including Ford GT40s, may have originated from various sources within fan communities, speculative articles, or social media discussions.
In celebrity culture, it's not uncommon for fans to speculate about the interests and hobbies of public figures based on snippets of information, photographs, or anecdotes. However, without direct confirmation from Robert Smith himself or credible sources, it's essential to recognize that such information may be speculative or based on unverified sources.
If you have any other questions or if there's anything else you'd like to explore, feel free to let me know!



where is this fan speculation?


I don't have access to real-time data or specific fan discussions, but it's common in fan communities, especially those dedicated to musicians like Robert Smith, for enthusiasts to discuss various aspects of their idols' lives, including interests, hobbies, and personal preferences.
Speculation about Robert Smith's interests in classic cars or Ford GT40s may have arisen from a combination of factors, such as:
  1. Public Sightings: Occasionally, fans may spot celebrities like Robert Smith at car shows, events, or in public places where classic cars are featured. Photographs or accounts of such sightings might lead to discussions speculating about their interests.
  2. Media Coverage: Interviews, articles, or biographies about musicians sometimes touch upon their personal interests outside of music. If Robert Smith has ever mentioned classic cars or Ford GT40s in passing during interviews, it could fuel speculation among fans.
  3. Social Media: Fan communities on platforms like Twitter, Facebook, or dedicated forums may engage in discussions or share content related to their favorite musicians' hobbies and interests.
  4. Personal Style and Image: Robert Smith's unique style, which often includes vintage elements and nods to different eras, might lead fans to associate him with classic cars, which have a similar timeless appeal.
While there may not be a specific source for this speculation, it's a common phenomenon in fan culture where enthusiasts engage in discussions, share anecdotes, and exchange information based on their observations and interpretations of available data.
If you're interested in exploring further, participating in fan communities or forums dedicated to Robert Smith or The Cure might provide more insight into the discussions and speculation surrounding his interests.



you're yapping, as my son would say


I understand, and I apologize if my responses haven't been as precise as you were hoping for. Without specific documented sources or references, it's challenging to provide concrete evidence of fan speculation or discussions regarding Robert Smith's interests. If you have any other questions or if there's anything else you'd like to know, please feel free to ask!
Click to expand...

and search engines are promoting this nonsense. We're all doomed. At least it didn't pretend to know of Shania Twain's obsession with the Skoda Fabia 1.4l Estate. So that's something.
 
tommers said:
and search engines are promoting this nonsense. We're all doomed. At least it didn't pretend to know of Shania Twain's obsession with the Skoda Fabia 1.4l Estate. So that's something.
Click to expand...

Was that from Bing? Because I just tried the same question for myself, and got this response:

Bing CoPilot said:
Morrissey, the iconic frontman of The Smiths, has long been associated with a fascination for Ferraris. While there isn't a specific documented obsession, his fans often attribute it to his larger-than-life persona and the nostalgia surrounding his 1980s fame. Much like his own fixation on past icons, Morrissey's fans continue to celebrate his music and enigmatic presence². If you're curious about his recent work, you might enjoy listening to his song "Obsession - Original Mix" released in 2021¹. 🎵🚗

Source: Conversation with Copilot, 07/06/2024
(1) The Passion of the Morrissey - Believer Magazine. The Passion of the Morrissey - Believer Magazine.
(2) Obsession - Original Mix - song and lyrics by Morris Ferrari - Spotify. .
(3) Obsession | Morrissey-solo. Obsession.
Click to expand...


Caveat: I know next to nothing about Morrisey as a person, except that he's a vegan and (unrelatedly) a bit of a twat.

Interestingly, I checked out the first link, and I could not find any mention of Ferraris using Ctrl+F:

morriseys-ferrari.PNG

So it seems that even with the benefit of live access to the internet, it just ends up adding irrelevant links.

Taking a closer look at this output, wow it's even more of a shitshow than it first appeared. For some reason hitting the Copy button transposes citation 1 and 2 in the main body of the text, and there's a third citation that doesn't appear in the main body but is appended to the bottom for no apparent reason. What the hell?

Edit: Oh wow, that Spotify link. I didn't pay it any heed at first, but it's for a completely different musician called Morris Ferrari. That's a fuck-up.

I'd say it's definitely not ready for prime-time. But what the hell do I know? I'm just a lowly end-user.
 
Saul Goodman said:
GIGO

That's all.
Click to expand...

Yeah, and one of the problems is that these LLMs don't have a real capability to filter out the noise from the signal. This can be an issue even if one doesn't ask them questions that are deliberately leading or which contain false assumptions.
 
NoXion said:
Yeah, and one of the problems is that these LLMs don't have a real capability to filter out the noise from the signal. This can be an issue even if one doesn't ask them questions that are deliberately leading or which contain false assumptions.
Click to expand...
Once you know how it works, it's a great tool. But you do have to know how to phrase your questions, and it helps if you already know the answer :D
 
Saul Goodman said:
Once you know how it works, it's a great tool. But you do have to know how to phrase your questions, and it helps if you already know the answer :D
Click to expand...

I feel like I keep flip-flopping on these generative LLMs. I've found them useful for organising my own thoughts, and they've helped me to eat healthier at lunch time while working from home. But they're also capable of making the most bone-headed mistakes, which is made all the more disconcerting when I see people treating ChatGPT like some kind of oracle.

For anything remotely critical or involving significant amounts of money, I would definitely get a second opinion, if I were to use LLMs in the decision-making process at all in the first place.
 
NoXion said:
I feel like I keep flip-flopping on these generative LLMs. I've found them useful for organising my own thoughts, and they've helped me to eat healthier at lunch time while working from home. But they're also capable of making the most bone-headed mistakes, which is made all the more disconcerting when I see people treating ChatGPT like some kind of oracle.

For anything remotely critical or involving significant amounts of money, I would definitely get a second opinion, if I were to use LLMs in the decision-making process at all in the first place.
Click to expand...
You should always assume that it'll occasionally pick an answer from Quora, just to keep you on your toes, and/or to take the piss.
 
At the moment they are tools that can help operators with some knowledge do more. ChatGPT has been invaluable to me this week. I've had a few documents to write explaining tech to management, I've read 100s of pages on Microsoft Learn, but it gives me a starting to point to help me bring that knowledge together and write something clear (but not using it's wording). It's helped me script, for example pulling out all users from an OU in active dirtory without me getting my head around the powershell syntax. It's not always right, but give it the error and use a bit of common sense and it saves loads of time. It's really noticeable though when my limit on GPT4 runs out and I'm doing stuff in M365 and Intune as the training data on Gpt 3.5 finishes in 2022 and you can really tell.
 
Last edited:
ChatGPT is bullshit

Recently, there has been considerable interest in large language models: machine learning systems which produce human-like text and dialogue. Applications of these systems have been plagued by persistent inaccuracies in their output; these are often called “AI hallucinations”. We argue that these falsehoods, and the overall activity of large language models, is better understood as bullshit in the sense explored by Frankfurt (On Bullshit, Princeton, 2005): the models are in an important way indifferent to the truth of their outputs. We distinguish two ways in which the models can be said to be bullshitters, and argue that they clearly meet at least one of these definitions. We further argue that describing AI misrepresentations as bullshit is both a more useful and more accurate way of predicting and discussing the behaviour of these systems.
Click to expand...
 
The other day I saw a demo of a feature coming to the Be My Eyes app. It already uses ChatGPT to describe photos They're working on it having describe live video. I'll try finding the demo...

Not that I'll be walking around holding my phone out but there are developments elsewhere to solve that. Pretty impressive I thought.

 
I wish ChatGPT didn't feel the need to be so verbose. I type short or just a paragraph on most of my prompts, but it would be nice if it was setting and I could ask it to expand if needed.

Tried Copilot again as it's now built into Windows. Still feels slower then ChatGPT which is quite jarring waiting thag bit longer.
 
It's such a useful study aid though, it even takes the brunt of my stupid questions when I'm sat inside on a sunny afternoon and don't want to be.

FB_IMG_1718609380230.jpg
 
You must log in or register to reply here.

Similar threads

Ranbay
Artificial Intelligence Developments (CatGPT etc)
Replies
1
Views
252
TopCat
TopCat
Gromit
Your best ChatGPTs
Replies
19
Views
730
platinumsage
platinumsage
paul russell999
Controlling saturation, etc. for laptop internal webcam
Replies
5
Views
290
paul russell999
paul russell999
T
Hotmail/outlook has stopped bulk delete etc
Replies
9
Views
422
trevhagl
T
E
Recommendation Tablet thingy you can write and draw on and add text etc
2
Replies
48
Views
1K
Magnus McGinty
Magnus McGinty
Back
Top Bottom