Truth is not a direction: a Tarski attack on LLM probes
Truth is not a direction: a Tarski attack on LLM probes Jul 10, 2026 • Abel Jansma A diagonal attack for LLM truth probes shows why no probe on a language model’s embedding space can pin down truth. A linear dream Modern LLMs famously encode input texts as vectors in some embedding space. One of the most satisfying discoveries about LLMs is that many natural concepts, like gender, emotions, capital cities, correspond to directions in this space.
- ▪Truth is not a direction: a Tarski attack on LLM probes Jul 10, 2026 • Abel Jansma A diagonal attack for LLM truth probes shows why no probe on a language model’s embedding space can pin down truth.
- ▪A linear dream Modern LLMs famously encode input texts as vectors in some embedding space.
- ▪One of the most satisfying discoveries about LLMs is that many natural concepts, like gender, emotions, capital cities, correspond to directions in this space.
Hacker News (AI / LLM) files mainly under ai. We currently carry 2,428 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Abel Jansma |
| Canonical URL | https://abeljansma.nl/2026/07/10/truth-is-not-a-direction.html |
| Publication time | Mon, 27 Jul 2026 12:56:36 +0000 |
| Retrieval time | 2026-07-27T13:06:18.014Z |
| Last seen | 2026-07-27T13:06:18.014Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | sLNODipGxTp_ · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Truth is not a direction: a Tarski attack on LLM probes Jul 10, 2026 • Abel Jansma A diagonal attack for LLM truth probes shows why no probe on a language model’s embedding space can pin down truth. A linear dream Modern LLMs famously encode input texts as vectors in some embedding space. One of the most satisfying discoveries about LLMs is that many natural concepts, like gender, emotions, capital cities, correspond to directions in this space. The extent to which a certain input text contains the concept “Male”, for example, can be quantified by the angle between the input’s embedding, and the direction corresponding to the “Male” concept. This is often referred to as the Linear Representation Hypothesis.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Abel Jansma.
Discussion
0 commentsMore from Abel Jansma
