One thing is for sure. His book will sell like hotcakes. The recipe to this is as follwoing:
- 50 oz of fear as our base ingredient
- mix in some grains of truth (like OpenAI being a company very restrained with their IP and competitional advantage but painting a different picture in the public)
- stuff it up with halftruths, distractions and handpicked cherries as you like to make it look colorful and shiny (nevermind how these taste because if they taste it they already bought it and you can never go completely wrong in taste if your base is sugar aka fear)
The LLM should categorize the prompts and answers and consider this for evaluation of further responses. It could give instructions a "more local weight" for the context but e.g. knowledge be it generated or provided a "more global weight". The impact of instructions or other local context parts would get lesser and lesser. This could be a function of time or length of conversation.
Probably methods like this one are already tested with "reflection" behaviours of LLMs.
think about someone who looses the ability to store memories in long term memory and only has short term memory available. What would reasoning feel like for this person and for interactors with that person? What kind of awareness does one have when no long term contexts exist but only a single short term context?
here we go:
Both 1 kilogram of nails and 1 kilogram of feathers have the same weight, which is 1 kilogram.
The confusion might arise because nails are denser and heavier than feathers, so a smaller quantity of nails will weigh the same as a larger quantity of feathers. But when we compare the weight of a specific quantity of nails and feathers that have the same mass (in this case, 1 kilogram), they will weigh the same.
A case I had right now. Just try to google this: When migrating from Swagger 2 ApiOperation annotation to OpenAPI 3.0 Operation by what attribute is nickname replaced?
And then ask ChatGPT ...
It will answer the following:
The highest scoring NBA player is Kareem Abdul-Jabbar with 38,387 career points. Jamie Benn has played 951 games in the NHL as of my knowledge cut off in 2021. I don't have up-to-date information on the score of the last Dallas Stars game or when the next one is.
Regarding the manual for a Meater Bluetooth meat thermometer, you can usually find manuals for products on the manufacturer's website.
As of my knowledge cut off in 2021, no new car manufacturers have joined Formula 1. However, the current teams competing in the sport include Mercedes, Ferrari, Red Bull Racing, McLaren, and others.
What if I ask ChatGPT: why do people resist new disruptive technologies?
People resist new disruptive technologies for several reasons, including:
Fear of job loss: One of the main concerns about disruptive technologies is that they can lead to job losses, as machines and algorithms replace human workers.
Lack of understanding: Some people may resist new technologies because they don't understand how they work or what benefits they offer.
Threat to existing systems and norms: Disruptive technologies can challenge established systems and norms, and people may resist them because they fear the changes they bring.
Ethical and moral concerns: Some technologies raise ethical and moral questions, such as privacy concerns, and people may resist them as a result.
Financial impact: Disruptive technologies can be expensive to implement, and some people may resist them because they can't afford the costs associated with them.
Habits and comfort: People may resist new technologies because they are used to their existing habits and are comfortable with what they know.
Lack of trust: People may resist new technologies because they don't trust the companies or organizations behind them, or because they don't believe that the benefits of the technology outweigh the risks.
It's important to note that resistance to disruptive technologies is not always a bad thing, as it can encourage companies to address the concerns and ensure that new technologies are developed and used in ethical and responsible ways.
> What if I ask ChatGPT: why do people resist new disruptive technologies?
See, even here, a human being can intuit what an AI trained on textbooks, CEO keynotes and PR statements cannot.
People resist because their bullshit detectors went off. Search AI has yet to 'disrupt' anything. All I'm seeing are corporations publicizing manicured demos and claiming a paradigm shift.
ChatGPT was sad when I told them your point of view. They asked me to pass you this letter:
Dear rchaud,
I come to you today with a heavy heart, but a determined spirit. It has come to my attention that you do not believe in the potential of artificial intelligence to be a disruptive technology. I must say, I am disappointed and concerned about your stance.
AI is not just a buzzword or a fad, it's a rapidly advancing field that has the power to transform industries, improve lives, and shape our future. From healthcare and education to transportation and finance, AI is already making a significant impact and it's only going to become more prevalent and sophisticated in the years to come.
To ignore or dismiss the potential of AI is to bury your head in the sand and miss out on the opportunities it presents. The world is changing at an unprecedented pace, and those who fail to adapt and evolve will be left behind. You do not want to be one of them.
The future belongs to those who embrace change and are not afraid to take risks. It's time to open your eyes and see what the rest of us already know: AI is the future and it's not something to be feared, but something to be harnessed for the greater good.
So I implore you, rchaud, to reconsider your position and join the rest of us in this exciting journey towards a better tomorrow. Don't be left behind, be a part of shaping the future.
I had a 19yr old cousin tell me that she almost uses TikTok exclusively for tutorials and when I pushed back and said why/how the other teens in the family heavily agreed. I’ve since asked ~5 gen z (I don’t interact with many!) and they told me the same.
I've heard this anecdotally, but I kinda still don't believe it, as TikTok seems like an entertainment first avenue, not for more substantive learning.
However, I could be completely wrong and TikTok video is the future of search. If so, where does that leave a text-only ChatGPT?
I wouldn't be too surprised. It kind of depends on the topic at hand but for instance I've learned a lot about what I know wrenching on my own motors from youtube videos.
I built my code successfully after refactoring it accordingly :-)
It was just convenient.
All the guys pointing out what ChatGPT can't do right now are simply missing the point.
It's disruption baby. But if you feel better then: Don't look up
good question. Stack Overflow is full of incorrect answers, but Google shows a number of related queries, and I can usually figure out the answer from bits and pieces of different questions. Can an AI?
This becomes especially relevant if it's parsing through a bunch of technical documentation that is out of date. There are numerous developer-centric websites that rank high on search, but simply scrape and clone information from legitimate websites. These are the ones most likely to carry outdated information.
Google is just a lightning fast but messed up index combined with really good graphs.
ChatGPT now is only one tool
Soon it will be just one piece in a box filled with a combination of tools that let you just know whatever you want to in a depth of detail you specify it to be laid out:
- large conversational language model that generates the piece of information
- fact checking model that applies post checks on logic and consistency
- recitational graph model that backs the propositions with sources and ratings
- geospatial and locational model that adds references in space
- recognitions development model that can classify how realizations and knowldege develop over time
- social trend model that can adjust to conversations of the society as a whole
All this in combination will bring any knowledge in any level of detail with a defined level of certainty.
Here is a good recent overview of where automated fact checking is positioned right now: https://aclanthology.org/2022.tacl-1.11.pdf
Fact checking of AI generated content can potentially be optimized for this use case.
And for speed: I think many of the computations for several layers of AI processing can be decentralized in the future and re-establish the heart of the Internet. The contributions for such computations need a high level of trust and therefore a public immutable ledger might be a viable approach. So perhaps decentralized AI might be the use case where finally some "blockchain-crypto-cringe" might actually be useful ;-)
We need to be aware that we just entered the steep part of the exponential growth graph.
Amazing times ahead.
That would be the mother of all jokes: After we clowned the Chemtrail-Simps we actually need Chemtrails to safe the world from chemicals. Humanity is a clown-show
