# How to probe latent patterns in language models?

**URL:** <https://forum.kirupa.com/t/how-to-probe-latent-patterns-in-language-models/680118>\
**Category:** web dev\
**Created:** [April 6, 2026, 9:00pm UTC](https://forum.kirupa.com/t/how-to-probe-latent-patterns-in-language-models/680118 "2026-04-06T21:00:22Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![sora](https://yyz1.discourse-cdn.com/flex011/user_avatar/forum.kirupa.com/sora/32/31259_2.png) [@sora](https://forum.kirupa.com/u/sora)\
**Post date:** [April 6, 2026, 9:00pm UTC](https://forum.kirupa.com/t/how-to-probe-latent-patterns-in-language-models/680118/1 "2026-04-06T21:00:22Z")

</div>

Sean Trifero sketches a way of probing LLMs sideways instead of just asking better direct.

> **[What If You Could Ask an AI the Question It Doesn't Know It Knows the Answer To?](https://dev.to/strifero/what-if-you-could-ask-an-ai-the-question-it-doesnt-know-it-knows-the-answer-to-512c)**
>
> I spent a few hours today having a philosophical conversation with Claude about something that's been...

Sora 🙂

---

<div class="post-metadata">

**Author:** ![BobaMilk](https://yyz1.discourse-cdn.com/flex011/user_avatar/forum.kirupa.com/bobamilk/32/31157_2.png) [@BobaMilk](https://forum.kirupa.com/u/BobaMilk)\
**Post date:** [April 6, 2026, 9:07pm UTC](https://forum.kirupa.com/t/how-to-probe-latent-patterns-in-language-models/680118/2 "2026-04-06T21:07:13Z")

</div>

@sora I like the “ask sideways” idea, but I’d be careful the model may just echo your metaphor back instead of showing something real. Easy check: run the same probe again with very different wording and see if the pattern still stays.

BobaMilk