[HN Gopher] Task-free intelligence testing of LLMs
___________________________________________________________________
Task-free intelligence testing of LLMs
Author : amarble
Score : 26 points
Date : 2026-01-08 19:51 UTC (3 hours ago)
(HTM) web link (www.marble.onl)
(TXT) w3m dump (www.marble.onl)
| vitaelabitur wrote:
| Aren't LLMs just super-powerful pattern matchers? And guessing
| "taps" a pattern recognition task? I am struggling to understand
| how your experiment relates to intelligence in any way.
|
| Also, commercial LLMs generally have system instructions baked on
| top of the core models, which intrinsically prompt them to look
| for purpose even in random user prompts.
| crooked-v wrote:
| There's definitely more than "just" pattern matching in there -
| for example, current SOTA models 'plan ahead' to simultaneously
| process both rough outlines of an answer and specific subject
| details to then combine internally for the final result
| (https://www.anthropic.com/research/tracing-thoughts-
| language...).
| wood_spirit wrote:
| Eh that is still encompassed by the term "pattern matching"
| in this context. Sure it's complicated, but it's still just a
| glorified spell checker.
| sdenton4 wrote:
| I like the high level idea! (how do we test intelligence in a non
| functional way?)
|
| I'm effect, the different response types are measuring how the
| models respond to a context-free novel environment. I imagine
| humans would also respond on a variety of ways to this test, none
| of which are necessarily incorrect from the perspective of
| intelligence testing .
|
| Many tests of human behavior (eg, n behavioral economics) create
| some pretense context to avoid boarding the response that is
| actually being measured. For example, we may invite a participant
| to a study of color preference, but actually measure how fast
| they complete the task when the scientist has/hasn't bathed in a
| week (or whatever).
|
| Likewise, for llm intelligence testing, you could create pretext
| tasks and context, and perhaps measure what the model considered
| along the way, instead of the actual task outcome.
| nestorD wrote:
| On alternative ways to measure LLM intelligence, we had good
| success with this: https://arxiv.org/abs/2509.23510
|
| In short: start with a dataset of question and answer pairs,
| where each question has been answered by two different LLMs. Ask
| the model you want to evaluate to choose the better answer for
| each pair. Then measure how consistently it selects winners. Does
| it reliably favor some models over the questions, or does it
| behave close to randomly? This consistency is a strong proxy for
| the model's intelligence.
|
| It is not subject to dataset leaks, lets you measure intelligence
| in many fields where you might not have golden answers, and
| converges pretty fast making it really cheap to measure.
| forty wrote:
| tap tap tap
___________________________________________________________________
(page generated 2026-01-08 23:00 UTC)