kind of crazy that models moving forward don't just strip all multi-numeral tokens. Would be great for llm providers, too, since their tokens consumed will go up.
How outdated information hides in LLM token generation probabilities
41–50 of 55 posts
Re: How outdated information hides in LLM token generation probabilities
#42Earlier quoted context omitted.
In that case you use RAG and have it tell you the source.
A RAG needs to be implemented by the LLM provider. The simple end user has no idea what that means, even though he will be (incorrectly) using the LLM for a vital purpose.
ChatGPT does exactly that with its built in runtime and web search.
But the LLM provider doesn’t have to do that. Langchain - the Python AI library - and OpenAI’s own library has support for third party tools.
It’s up to third parties to build on up of it.
Re: How outdated information hides in LLM token generation probabilities
#43Prompting Claude to show the ambiguity:
Tell me the height of Mountain Bartle Frere. Please don't output any long text, also don't output a single height if you saw multiple heights around. Give me a list of potential heights cited around.
LLM:
Mount Bartle Frere in Queensland, Australia has commonly cited heights of:
1,622 meters (5,322 feet)
1,611 meters (5,285 feet)
Since this is quite specific geographic information that may appear in only a few sources, I should note that I may hallucinate details - you should verify these numbers.
Re: How outdated information hides in LLM token generation probabilities
#44Earlier quoted context omitted.
But this is the same problem - Wikipedia is a secondary source and should always get overruled by the primary source.
And there are documented cases of concentrated efforts to manipulate the content of Wikipedia.
You’re probably being facetious but just in case:
https://www.bbc.com/news/technology-28481876.amp
https://www.bbc.com/news/technology-58559412.amp
(With apologies for amp links)
Re: How outdated information hides in LLM token generation probabilities
#45Prompting Claude to show the ambiguity: Tell me the height of Mountain Bartle Frere. Please don't output any long text, also don't output a single height if you saw multiple heights around. Give me a list of potential heights cited around. LLM: Mount Bartle Frere in Queensland, Australia has commonly cited heights of: 1,622 meters (5,322 feet) 1,611 meters (5,285 feet) Since this is quite specific geographic informat…
I asked a bunch of LLMs using your prompt. The only change was to just use meters.
https://beta.gitsense.com/?chat=bb57a248-e14a-4f33-bbe9-2fa9...
1622m is most agreed upon. The interesting numbers are the ones with less than 50% agreement. Not sure if they are hallucinations or if they are outdated data.
Click the conversation link in the user message bubble to see the response from each LLM.
Re: How outdated information hides in LLM token generation probabilities
#46> The scenario that I’m worried about, and that is playing out right now, is that they get good enough that we (or our leaders) become overconfident in their abilities and start integrating them into applications that they just aren’t ready for without a proper understanding of their limitations. Very true.
I would say this is true until we hit a "oh shit, they can really sue us, even if we warn them" moment. I'm imagining legislation will come into play that will make it less ideal for business critical solutions. I know Air Canada has been sued and probably others.
I still think we are in the honeymoon phase, and once that is over, LLM will become what it is meant to be, which is a power tool for domain experts.
Re: How outdated information hides in LLM token generation probabilities
#47Earlier quoted context omitted.
It is happening in insurance right now and it is an unmitigated disaster that nobody wants to address. There is real data used for insurance premiums and claims payouts but it's being swapped out for AI slop, and the sales folks are getting bonuses for selling hot garbage and the executives are getting bonuses for buying hot garbage.
Huh, if sales uses AI/LLMs and succeeds with it, as it seemed to me youve implied with their bonuses ... Isn't that actually positive for the company? Or do you mean they succeed by promising lies via AI?
Not OP but I could see this being short term savings related to the cost of sourcing/generating risk data leading to bonuses prior to the deficiencies in that risk model being exposed in claims long term.
Re: How outdated information hides in LLM token generation probabilities
#48Earlier quoted context omitted.
It is happening in insurance right now and it is an unmitigated disaster that nobody wants to address. There is real data used for insurance premiums and claims payouts but it's being swapped out for AI slop, and the sales folks are getting bonuses for selling hot garbage and the executives are getting bonuses for buying hot garbage.
Huh, if sales uses AI/LLMs and succeeds with it, as it seemed to me youve implied with their bonuses ... Isn't that actually positive for the company? Or do you mean they succeed by promising lies via AI?
[dead]
Re: How outdated information hides in LLM token generation probabilities
#49Earlier quoted context omitted.
And there are documented cases of concentrated efforts to manipulate the content of Wikipedia.
You’re probably being facetious but just in case: https://www.bbc.com/news/technology-28481876.amp https://www.bbc.com/news/technology-58559412.amp (With apologies for amp links)
I was most certainly not being facetious.
Re: How outdated information hides in LLM token generation probabilities
#50Earlier quoted context omitted.
It is happening in insurance right now and it is an unmitigated disaster that nobody wants to address. There is real data used for insurance premiums and claims payouts but it's being swapped out for AI slop, and the sales folks are getting bonuses for selling hot garbage and the executives are getting bonuses for buying hot garbage.
Huh, if sales uses AI/LLMs and succeeds with it, as it seemed to me youve implied with their bonuses ... Isn't that actually positive for the company? Or do you mean they succeed by promising lies via AI?
The industry is insurance. If you offload your due diligence to an AI that's wrong, the company will go underwater. What if the LLM tells you it's found a great market with little competition, high net worth individuals, etc. etc. and you don't check and end up making all your sales in the hills of California in wildfire country?