Likely growth of AI - how can investors position themselves?

Exodi

Linton said:

Exodi said:

Malthusian said:

The holy grail of AI research is a robot that will teach itself to walk without being told to, and more generally to form its own goals and carry them out. Once a robot can do that better than we can, the Singularity has occurred and all human bets are off. Some people are very narrowly defining AI to mean that kind of intelligence, which creates an infinite pool of semantic arguments with people who think that AI is a self-service checkout.

This is what I was going to touch upon - true AI being defined by having free will and sentience.

The day an AI responds "I don't feel like doing that" without a programmer coding the specific condition for that response.

I won't get into the whole 'I, Robot' scenario, a lot of people already have an irrational fear of AI.

I do look forward to the first unexpected response of:

"Hey ChatAI, can you tell me where the closest place to buy a cheap toaster is?"
"No, look yourself".

Free will and sentience is another deep philosophical matter but best not to go there.

More importantly for this forum I dont think an AI with a teenage mentality would provide a lucrative investment opportunity.

Or if such AI advances existed, whether the AI would tell you in the first place or keep it to themselves? Maybe they'll mislead you.

Sorry off topic.

Most of these threads recently don't appreciate that chatbots aren't'AI' and effectively regurgitate past data in a convenient format. We must find something to talk about.

Plus even if it did exist, I don't think BlackRock would allow the lowly public access. Most people don't even know of the existence of Aladdin.

Malthusian

Exodi said:

"Hey ChatAI, can you tell me where the closest place to buy a cheap toaster is?"
"No, look yourself".

ChatGPT will already reply to that with something like "As an AI language model, I do not have the ability to access the Internet or provide real-time information. Therefore, I cannot provide you with specific links to toaster shops in your area or comment on which will sell toasters for the lowest cost. It is always advisable to consult with a qualified and regulated toaster adviser for the most accurate and up-to-date information. Here are some general steps you can follow to find a toaster professional in your area..." 
Which is basically the same thing.
Bing AI will convert the question into a search string "closest place cheap toaster" and then put it into Bing, right in front of you, which is essentially letmegooglethatforyou.com with a lower-grade search engine.

Exodi

Malthusian said:
It is always advisable to consult with a qualified and regulated toaster adviser for the most accurate and up-to-date information. Here are some general steps you can follow to find a toaster professional in your area..." 

I don't know why, but this part made me laugh in person.

Sorry, I keep thinking of Bard (which does access live prices - pretty impressive from my tests with similarly framed questions) instead of ChatGPT which I haven't used much.

Millyonare

Malthusian said: 

In any real "IQ test" the verbal-linguistic part is only part of it. If ChatGPT scores zero on all the "which polyhedron matches this one" questions and finishes with an IQ of 82, it doesn't mean anything more than the score of 147.

Today, 147 in a verbal test. Tomorrow, 200. The day after that, 200 in a working memory test. And so on. Few people realize, AI does not stand still. It learns while humans are asleep. The 147 IQ score today is just the foothills of AI's climb to the future summit of Everest.

L9XSS

Graphcore is one I’m reading and researching about. Private investor backed company at present and its UK based.

Nebulous2

Malthusian said:

Exodi said:

"Hey ChatAI, can you tell me where the closest place to buy a cheap toaster is?"
"No, look yourself".

ChatGPT will already reply to that with something like "As an AI language model, I do not have the ability to access the Internet or provide real-time information. Therefore, I cannot provide you with specific links to toaster shops in your area or comment on which will sell toasters for the lowest cost. It is always advisable to consult with a qualified and regulated toaster adviser for the most accurate and up-to-date information. Here are some general steps you can follow to find a toaster professional in your area..." 
Which is basically the same thing.
Bing AI will convert the question into a search string "closest place cheap toaster" and then put it into Bing, right in front of you, which is essentially letmegooglethatforyou.com with a lower-grade search engine.

Except it does have the ability to access the internet.

An acquaintance wanted chat GPT to read and comment on a terms and conditions document.

I can't do that as I cannot access the internet.

Is there anyway I can send a document to you so you can analyse it? 

No - but you can send me a link. 

He sent a link and ChatGPT accessed the document. He wasn't impressed with its understanding, when he asked it about some specific details. 

 

 

Cus

Exodi said:

Linton said:

Exodi said:

Malthusian said:

The holy grail of AI research is a robot that will teach itself to walk without being told to, and more generally to form its own goals and carry them out. Once a robot can do that better than we can, the Singularity has occurred and all human bets are off. Some people are very narrowly defining AI to mean that kind of intelligence, which creates an infinite pool of semantic arguments with people who think that AI is a self-service checkout.

This is what I was going to touch upon - true AI being defined by having free will and sentience.

The day an AI responds "I don't feel like doing that" without a programmer coding the specific condition for that response.

I won't get into the whole 'I, Robot' scenario, a lot of people already have an irrational fear of AI.

I do look forward to the first unexpected response of:

"Hey ChatAI, can you tell me where the closest place to buy a cheap toaster is?"
"No, look yourself".

Free will and sentience is another deep philosophical matter but best not to go there.

More importantly for this forum I dont think an AI with a teenage mentality would provide a lucrative investment opportunity.

Or if such AI advances existed, whether the AI would tell you in the first place or keep it to themselves? Maybe they'll mislead you.

Sorry off topic.

Most of these threads recently don't appreciate that chatbots aren't'AI' and effectively regurgitate past data in a convenient format. We must find something to talk about.

Plus even if it did exist, I don't think BlackRock would allow the lowly public access. Most people don't even know of the existence of Aladdin.

Why would most people even need to know about a trade order routing system?

adindas

adindas said:

Big-name investors Choices:
https://markets.businessinsider.com/news/stocks/billionaire-investors-ai-chatgpt-bill-ackman-stanley-druckenmiller-big-tech-2023-5 
Big-name investors are going all-in on AI George Glover May 18, 2023

In the current state of hardware in no microchip / Graphics card  manufacturers could beat Nvidia (NVDA) to enable the AI revolution.

But NVDA valuation is still very expensive compared to  other microchip / Graphic card  manufacturers. However high growth stock is difficult to value, so should not be solely based on their valuation like typical in value stock.  Depending solely on their valuation like in  value stock you might miss a lot of opportunities.

There is a recent coverage of NVDA technical analysis from CNBC Chartmaster

https://www.youtube.com/watch?v=K5l67YZDNZY

From Fundamental Analysts, Valuation Model

Brief Summary

Price / Earnings

P/E excluding extraordinary items - LFY202.40

P/E excluding extraordinary items high - TTM144.21

P/E excluding extraordinary items low - TTM26.56

P/E Basic excluding extraordinary items - TTM143.18

P/E Normalized - LFY170.23

P/E including extraordinary items - TTM202.40

Price / Sales

Price to sales - LFY35.71

Price to sales - TTM37.22

Price / Book

Price to book - TTM39.28

Price to book - LFY43.46

Price to tangible book - MRQ51.93

Price to tangible book - LFY60.00

Price / Free cash flow

Price to free cash flow per share - LFY282.46

Price to free cash flow per share - TTM204.76

Net debt

Net debt - MRQ-4.37B

Net debt - LFY-2.34B

Dividend yield0.04%

Current dividend yield - Common stock primary issue - TTM0.04%

Dividend yield - 5Y average0.12%

Sometimes High valuation is justifiable if the company has "moat" and matched with enormous growth and they do not miss earning expectation. The stock like this will get severely punished by mr market if they miss the earning expectation. It is not uncommon -20%+ in just a few days.

Gary1984

My suggestion would be to just invest in a global equity tracker. The obvious winners such as chip makers and big tech will already have expected gains priced in. 

AI is so novel that it's hard to predict who'll be able to utilise it most effectively for future growth so just cover all your bases. Could be bio tech to develop new drugs, energy companies developing new synthetic fuels or nuclear fusion, healthcare using it for diagnosing disease, carmakers developing self driving, agriculture automating and optimising the growing of crops, retailers predicting fashion trends etc.  Who knows?

Or maybe it will be a damp squib, in which case you won't lose out by backing everything.

Malthusian

Nebulous2 said:

Except it does have the ability to access the internet.

No it doesn't. It can however provide its best guess as to what someone who does have access to the Internet would say. That is all a chatbot does.

He sent a link and ChatGPT accessed the document. He wasn't impressed with its understanding, when he asked it about some specific details. 

It pretended it had accessed the document. Actually, "pretended" is wrong; it made its honest best guess as to what someone who had accessed the document would say. (I.e. "I have accessed your document.") That is what it is designed to do. 

He wasn't impressed with its understanding, when he asked it about some specific details. 

It then tried to blag its way through further answers (or rather it made its best guess as to what someone who had accessed the terms and conditions document would say in response to your friend's questions). Unsurprisingly, it got them wrong because it didn't know what the actual document said.  

And yet your friend drew the conclusion that was the exact opposite of the evidence. As you describe it, "Beep beep, I have accessed the document" was enough to convince your friend that ChatGPT could freely access the Internet. The subsequent test (can ChatGPT accurately answer specific questions about the document) was discarded as irrelevant because it demonstrated the opposite of what he'd already decided was true.

See what I mean about the weakness of the Turing test as applied to humans? Your friend could put me in a cage without a computer, give me the link and ask me questions about the document. I would get lots of details wrong, but I could probably still give him the impression that I had read it through a combination of guessing and cold-reading. He'd apparently prefer to believe "Malthusian is a cyborg and has a Wifi aerial in his skull" over "Malthusian has tricked me". 

(NB: I ran this test myself and the result was "As an AI language model, I am unable to browse the internet or access external links, so I won't be able to view the terms and conditions document directly through a URL." As expected. It is likely that the bot has been updated since your friend's confusion to increase the likelihood that it says "I can't access URLs" instead of responding in the persona of someone who has accessed the URL.)