AI Tells: Opus 5.5 Update
Comparisons use articles on 9,974 aligned topics, except mannered prose, which uses a 1,000-topic subsample. Mannered-prose values are mean scores assigned by Claude Opus 5 on a 0–100 scale. Tell counts include words, phrases, and frames used at least twice the human rate and meeting frequency and frame filters.
- ▪Comparisons use articles on 9,974 aligned topics, except mannered prose, which uses a 1,000-topic subsample.
- ▪Mannered-prose values are mean scores assigned by Claude Opus 5 on a 0–100 scale.
- ▪Tell counts include words, phrases, and frames used at least twice the human rate and meeting frequency and frame filters.
Hacker News (AI / LLM) files mainly under ai. We currently carry 7,526 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
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 | Graphite |
| Canonical URL | https://graphite.io/five-percent/research/ai-tells-opus-5-5-update |
| Publication time | Sun, 04 Oct 2026 12:04:02 +0000 |
| Retrieval time | 2026-10-04T12:19:53.726Z |
| Last seen | 2026-10-04T12:19:53.726Z |
| 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 | None |
| Cluster logic | Not yet clustered, or no peer story found in the clustering window. |
| 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
Research // Published October 1, 2026AI Tells: Opus 5.5 UpdateGregory Druck, PhDChief AI OfficerJose Luis Paredes, PhDSenior Data SpecialistEthan SmithCEOContentsCopy linkDiscuss with AIAI Tells: Opus 5.5 UpdateClaude’s Word Choice Is Becoming More Human, While GPT’s Is Becoming Less HumanWord-Distribution Divergence From Human Writing Across Model VersionsClaudeGPTOpus 5.5 Uses Less Mannered Prose Than Opus 5, but Still More Than AstraMannered-Prose Scores Across Model VersionsClaudeGPTOpus 5.5 Uses Em Dashes 99% Less Often Than Opus 5Em Dash Use Across Claude Model VersionsOpus 5.5 Still Has 2,548 TellsNumber of AI Tells Across Claude Model VersionsSource: Graphite research, AI Tells: Opus 5.5 Update (2026).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Graphite.
Discussion
0 commentsMore from Graphite
