Quote:
Originally Posted by Fuzz
It's still just a model predicting the next words in the sequence. All your examples tell us its it has a good source to draw from. Which also exposes one of the risks using these. If all the sources for a subject are wrong, or, say, 50/50, and the LLM doesn't tell you that, you can be misled.
Had you not specified "Alberta" in your query, you may have been given examples for the US instead of Canada, and then jurisdictional confusion might have you looking like Danielle Smith. So it is important to specify specifics if you plan on using it for anything serious, and part of that is knowing which specifics need to be presented to the model, which could be a challenge.
|
Not quite sure what you are trying to argue here. Of course if I gave Alberta as jurisdiction I would get rulings based in Alberta. If I didnt specify a jurisdiction I mean that should be very obvious and clear you need to give context to get an answer? Would you answer such a question without context.
Ask Joe Bloe on the street and he will tell you though. the AI model can also represent Joe Bloe and his answer if you arent concise in the request. This is an all emcompassing AI language model and the error is in failing to provide context for the AI to answer.
In the pizza case I just gave, the AI model effectively ruled against its own pizza law that I made up for him that the law itself would be unconstitutional and cited a Canadian case.
Dont give a context or persona and you get the routine that TorqueDog got.
Try it out for yourself in a subject you are knowledgeble about and you can determine for yourself if its accurate, or poor. It has its strengths and still has its weaknesses but those weaknesses are disappearing with every iteration.
Oh and I have something for you. I asked a new chat the exact same question with a similar ruling but here is what I got regarding court cases when I did NOT specify a jurisdiction. Be sure to read the end.
ME
Do you have court cases to refer to, to justify your case?
Spoiler!
In crafting a legal decision for a small claims case, it is important to note that small claims courts often do not rely heavily on precedents as they are designed to be more informal and accessible to the general public. However, I can provide some general legal principles that could apply to this case, which may be found in analogous court decisions.
Breach of Contract: In cases involving breach of contract, courts often look to past decisions for guidance on determining whether a breach has occurred and the appropriate remedy. In this instance, the Defendant's failure to deliver the work as promised and charging a substantially higher amount than originally agreed upon could be considered a breach. A relevant case in this context could be Hadley v. Baxendale (1854) 9 Exch 341, a seminal case establishing the rule for consequential damages in contract law.
Damages: In awarding damages, courts typically aim to put the injured party in the position they would have been in had the contract been properly performed. This is referred to as the "expectation measure" of damages. A case that discusses the calculation of damages in the context of breach of contract is Peevyhouse v. Garland Coal & Mining Co., 382 P.2d 109 (Okla. 1962). This case illustrates the principle that damages should be tailored to the specific circumstances of each case and can include restitution of the original payment, as well as additional damages for any harm or loss suffered as a result of the breach.
While these cases may not be directly applicable to a small claims matter, they provide general principles that could be useful in understanding the legal framework for breach of contract and damages. It's important to research and identify cases from the jurisdiction in which the small claims case is being heard, as laws and precedents may vary between jurisdictions.
Its a heck of a lot better at reasoning and logic then some are willing to give it credit for.