News for hackers. Stuff that matters.
Re:Hallucination is inevitable: An innate limitation of larg... by andsoitis on Sunday February 25, 2024 @11:21AM (#39502037)
> It will happily execute this algorithm. For large numbers, it is slightly off on the arithmetic. When I asked it to double check, it did so using Python code. After that, it kept using Python code to perform the math. It was also able to reason intelligently about different outcomes if always picking a (or b) given different starting points.

Notice that you had to notice the error and had to prompt it to double check. Lots of complicated things going on here. Many (most?) humans will fail somewhere along this trajectory.

Did it double check the Python code to make sure it is correct (not just in the sense that it is valid, executable code, but that it is the correct check in the first place)? Or did you double check that its modified algorithm is correct? Fool me once and all that…

Upon reflection it appears as if you have a heuristic (algorithm? that leverages logic, awareness, critical thinking, experience, a goal in mind, intuition, etc. to push towards better results.

“It was able to reason intelligently” imbues qualities that I am skeptical is reasonable to attribute to this very narrow domain - what’s an example where it showed intelligent reasoning capabilities?

Re:Hallucination is inevitable: An innate limitation of larg... by fl7305 on Sunday February 25, 2024 @01:44PM (#39503498)
> Notice that you had to notice the error and had to prompt it to double check. Lots of complicated things going on here. Many (most?) humans will fail somewhere along this trajectory.

Sure. This was covered by my statement above: "These algorithms are incomplete and buggy".

> “It was able to reason intelligently” imbues qualities that I am skeptical is reasonable to attribute to this very narrow domain - what’s an example where it showed intelligent reasoning capabilities?

Here's an example. I asked it to analyze the case where we always pick option "b" in my example above. It took my word problem and boiled it down to an equation:

  ChatGPT: To find the threshold where the behavior switches from decreasing to increasing when always choosing option "b", we need to identify the smallest integer starting value that, after being doubled and reduced by 40, leads to an equal or larger integer in the next iteration. We're looking for the smallest integer x where 2x - 40 >= x 
This was part of a longer conversation where it analyzed different properties and outcomes of the "game rules" that I gave it.

As you pointed out, it got some things wrong and had to be corrected. But Socratic reasoning works fairly well to guide it. It can find errors in its own reasoning. For instance, if asked to actually calculate a few iterations for a given case, it will find its own errors in its claims about that case.

Is it useful right now? Maybe, maybe not, depends on your use case. It definitely takes a lot of thinking on your own and guiding it. At some points it goes from seemingly intelligent to downright pigheaded and stupid.

But in my view there is absolutely no way a lookup table algorithm can contain enough data to be anywhere near the level of responses we're seeing here.