[source99]

This is one of my favorite test cases:

Prompt: Here is a riddle. It is a common riddle but with some changes that make it more difficult. You are an alien that will live for at least 10000 years. You have no sense of temperature. you can not feel hot or cold. you have eyes and can see. you are in a house. downstairs are 3 light switches that control 3 light bulbs that are upstairs. Each light bulb will last for exactly 3 years. you can tell by looking at a bulb if it has burned out after 3 years. devise a strategy to determine which switch controls which light. ChatGPT 4 The standard solution to this problem involves using the heat generated by the bulbs, but since you as an alien can't feel temperature, we need to utilize the fact that these bulbs have a specific lifespan of 3 years. Here's a strategy:

Turn on the first switch and wait for 3 years. After 3 years, turn it off.

Right after turning off the first switch, turn on the second switch.

Leave the third switch off throughout this process.

Now, go upstairs to inspect the bulbs:

The bulb that is off and has burned out is controlled by the first switch. This bulb was turned on for 3 years, so it has reached the end of its lifespan and burned out.

The bulb that is on is controlled by the second switch. You turned this on right after turning off the first switch, so it's still functioning.

The bulb that is off and hasn't burned out is controlled by the third switch. This switch was never turned on, so the bulb is still in a brand-new condition.

This strategy ensures that you can confidently identify which switch controls which bulb.

[stubybubs]

It's telling that it didn't pick up on the fact that the whole "once you look you can't touch the switches anymore" isn't in this version of the riddle. I mean the obvious strategy in this case is turn on the first switch, go upstairs, look at the bulbs. Go back downstairs and try the second switch. You've not got them all mapped out in about 30 seconds.

Using GTP4 I asked if there was a way to do it in less than 3 years, but it couldn't figure this out even if I told it you can look and use the switches as much as you want. Instead it suggested turning on a switch for 10 minutes, then using your "excellent alien vision" determine which 3 year lifespan bulb has 10 minutes of wear on it.

Makes me think GPT4 doesn't really have better reasoning, it just looks like better reasoning because it's been fed way more data.

[tedunangst]

Variants of common riddles remain the final frontier. I'm trying to cross the river in a canoe with a carrot, cabbage, and cucumber...

[famouswaffles]

Variants of common riddles actually can be solved with GPT-4, but you have to rewrite it so it doesn't look like the riddle from memory(sometimes, it's as easy as changing names to something completely different). Turns out Language models trust their memory quite a bit. Slightly related - they won't actually use the results of tools if it differs a lot from what it expects the output to be - https://vgel.me/posts/tools-not-needed/

[nathan_compton]

"Language models trust their memory quite a bit."

All they have is memory, either in the weights or the input prompt. To the extent that these models appear to reason, it is precisely in the ability to successfully substitute information from the prompt into reasoning patterns in the training data. It shouldn't be any surprise that this fails when patterns in the prompt strongly condition the model to reproduce particular patterns of reasoning (eg, many words in the riddle indicate a well known riddle, but the details are different).

I know the impulse to anthropomorphize is almost impossibly seductive, but I find that the best way to understand and use these models is to remember: they are giant conditional probability distributions for the next token.

[famouswaffles]

LLMs trained on code reason better. Perform better on reasoning benchmarks even if the benchmarks have nothing to do with code. You're wrong.

https://arxiv.org/abs/2210.07128

[nathan_compton]

Code is often just a sequence of steps (sometimes with comments to indicate goals). As such, it is just another form of patterns of reasoning. Many chains of thought that you would utilize in code are useful skeletons to think about other things.

I don't see how this undermines my point.

[stubybubs]

This really just makes it seem like it's not reason at all. The trick (or rather un-trick) here is that you can look at the bulbs as many times as you want. Even if I explicitly tell GPT4 that, it doesn't get it.

It's not reason, it's mapping.

[BoiledCabbage]

Maybe I'm missing something, but this seems like a really poorly worded riddle. Or just a bad riddle.

Given what you stated, the solution would be walk upstairs look at the 3 bulbs, walk downstairs switch one of the switches. Walk upstairs see which bulb changed on/off. Repeat for the other two switches.

This takes roughly 5 mins rather than your solution which takes 3 years.

[pillefitz]

You're missing and getting the point at the same time.

Your solution would be the correct one, while GPT pulls out the "only look once"-constraint out of nowhere. The riddle is perfectly fine.

[BoiledCabbage]

Ah thanks, that clears it up. The formatting made me miss that that was the ChatGPT response. I thought that was the user sharing their solution that they look for.

[SkyPuncher]

This is the crux of the problem for GPT, enough of the text is from the “standard” riddle that is cannot break from it to actually answer the question.

I’m seeing this all of the time when trying to get GPT to perform certain answering problems. It’s heavily biased towards the “correct” answer - even when the prompt presents directly contradictory information.

[redox99]

Except the part about "with some changes that make it more difficult" is false. The changes make it trivial.

Edit: Omitting that part still makes GPT4 over complicate the solution

[mirekrusin]

You just passed the test that you're not LLM.

[lakis]

The reply is funny. I told ChatGPT that it can do multiple trips and that it can see both switches and light bulbs at the same time. ChatGPT keeps insisting that you have to turn on a switch, wait a few minutes , flip switch to off, turn other switch to on, then go and look and feel the switches. The classic solution to the riddle.

  But if you can see both switches and light bulbs, you turn on one switch, you see which bulb turn on. You then turn on the 2nd switch and see which light turn on. You are done. No wait needs to happen ;-)

[nathan_compton]

"feel the switches"?

[mirekrusin]

Arguably LLMs are handicapped by tuning that always expects some answer without questioning the question.

[bluepoint]

Actually, this is a really good point. Asking a question means that you have an internal model or the world and you realize that there are some data that is way off. Is it even possible at all to train an LLM to ask a question? This also gives me an idea for the future where most online text is generated by AI: we will play the game of responding questions with questions and then we know we are human!

[oh_sigh]

Are you looking for: turn one light on, walk upstairs and note the light that is on. Walk downstairs, turn another light on, walk upstairs and note the new light that is on. Now you know which switches control which lights and it only took you 5 minutes instead of 6 years