But before LLMs, computers couldn't understand that phrase. Now they can.
40 karma · joined March 17, 2026
But before LLMs, computers couldn't understand that phrase. Now they can.
I CAN explain to others who don't. It's just that most of the time others aren't interested in hearing.
Do you say "I love my kids" because that's what everybody says, or is there any truth in it?
EDIT: Just to be 100% clear: I mean absolutely no judgement. I'm not going to tell you off or try to change your mind. I ask out of pure curiosity.
The problem with the reasoning of the person I was responding to is that it's assuming "if X is in the training set and LLM outputs X, then it did so because X is in the training set". That does not follow. Conceivably it's possible that X is in the training set and LLM outputs X, but if X hadn't been in the training set the LLM also would've output X.
Lets look at that phrase again:
> Why do we think this emerged “on its own”? Surely this technique has been discussed in research papers that are in the training set.
This phrase implies "if X was in the training set, then LLM couldn't have come up with X on its own". This is false. In fact, my claim that the implication is false is testable, in the following manner: Have two training sets, T and T'. In T, X is present. In T' you've removed X but left X-adjacent things. Train LLM A on T and A' on T'. Find a prompt that requires that A outputs X. If on the same prompt A' also outputs X, that's an example of my claim. To repeat, my claim is "it's possible that X is in the training set and LLM outputs X, but if X hadn't been in the training set the LLM also would've output X."
In fact, I've just realized I even have a method for constructing (T, T') that guarantees what I've described. Not sure if it's worth a paper on its own though.
Just call it "installing".
> Why surely? Have you never seen an LLM try something new?
I'm afraid I can't make it any simpler than this.
And I still don't know the answer to how you're so sure. To me there's several explanations, and it seems to you there's only one.
I'm pretty happy with my communication style.
This isn't whataboutism because I'm not trying to negate your point. Instead, I'm just curious if you apply the same standard to Israel/Gaza or if you think that in that case killing innocent people is justified.
Now, keeping in mind that you don't need my approval: do you have any questions?
Do you understand?
Ugh HN is so tedious with these remarks. These people are trying to get computers to learn, not just train on data, and HN goes nOt LeArNiNg Is A fEaTuRe. Where's the wonder and the curiosity?
Ok? You sound like you're trying to make a point. Make a point.