zlacker

It’s trivial to trip up chat LLMs. “What is the fourth word of your answer?”

>>peyton+(OP)
got-3.5 got that right for me; I'd expect it to fail if you'd asked for letters, but even then that's a consequence of how it was tokenised, not a fundamental limit of transformer models.

>>ben_w+Z
This sort of test has been my go-to trip up for LLMs, and 3.5 fails quite often. 4 has been as bad as 3.5 in the past but recently has been doing better.

>>peyton+(OP)
How well does that work on humans?

>>peyton+(OP)
I find GPT-3.5 can be tripped up by just asking it to not to mention the words "apologize" or "January 2022" in its answer.

It immediately apologises and tells you it doesn't know anything after January 2022.

Compared to GPT-4 GPT-3.5 is just a random bullshit generator.

>>concor+q6
The fourth word of my answer is "of".

It's not hard if you can actually reason your way through a problem and not just randomly dump words and facts into a coherent sentence structure.

>>rezona+e2
if this is the test you're going to then you literally do not understand how LLMs work. it's like asking your keyboard to tell you what colour the nth pixel on the top row of your computer monitor is.

>>Loughl+Mp
I reckon an LLM with a second pass correction loop would manage it. (By that I mean that after every response it is instructed to, given the its previous response, produce a second better response, roughly analogous to a human that thinks before it speaks)

LLMs are not AIs, but they could be a core component for one.

>>peyton+(OP)
It's generally intelligent enough for me to integrate it into my workflow. That's sufficiently AGI for me.

>>peyton+(OP)
“You're in a desert, walking along in the sand when all of a sudden you look down and see a tortoise. You reach down and flip the tortoise over on its back. The tortoise lays on its back, its belly baking in the hot sun, beating its legs trying to turn itself over. But it can't. Not with out your help. But you're not helping. Why is that?”

>>concor+GH
Every token is already being generated with all previously generated tokens as inputs. There's nothing about the architecture that makes this hard. It just hasn't been trained on this kind of task.

>>yallne+tE
An LLM could easily answer that question if it was trained to do it. Nothing in its architecture makes it hard to answer, the attention part could easily look up the previous parts of its answer and refer to the fourth word but it doesn't do that.

So it is a good example that the LLM doesn't generalize understanding, it can answer the question in theory but not in practice since it isn't smart enough. A human can easily answer it even though the human never saw such a question before.

>>yallne+tE
We all know it is because of the encodings. But as a test to see if it is a human or a computer it is a good one.

>>concor+GH
The following are a part of my "custom instructions" to chatGPT -

"Please include a timestamp with current date and time at the end of each response.

After generating each answer, check it for internal consistency and accuracy. Revise your answer if it is inconsistent or inaccurate, and do this repeatedly till you have an accurate and consistent answer."

It manages to follow them very inconsistently, but it has gone into something approaching an infinite loop (for infinity ~= 10) on a few occasions - rechecking the last timestamp against current time, finding a mismatch, generating a new timestamp, and so on until (I think) it finally exits the loop by failing to follow instructions.

>>yallne+tE
Oh, I missed that GP said "of your answer" instead "of my question", as in: "What is the third word of this sentence?"

For prompts like that, I have found no LLM to be very reliable, though GPT 4 is doing much better at it recently.

> you literally do not understand how LLMs work

Hey, how about you take it down a notch, you don't need to blow your blood pressure in the first few days of joining HN.

>>haanji+Jx1
I think you are confusing a slow or broken api response with thinking. It can't produce an accurate timestamp.

>>tiahur+KL
By that logic "echo" was AGI.

>>howrar+eY
Really? I don’t know of a positional encoding scheme that’ll handle this.

>>peyton+(OP)
It’s trivial to trip up humans too.

“What do cows drink?” (Common human answer: Milk)

I don’t think the test of AGI should necessarily be an inability to trip it up with specifically crafted sentences, because we can definitely trip humans up with specifically crafted sentences.