I compared Claude Opus 4.8 with 4.7 in a 10-round honesty test - and a legal prompt broke it
The comparison between Claude Opus 4.8 and 4.7 revealed that the newer model performs better in terms of honesty and judgment. However, a significant judgment error in Opus 4.8 indicates that there is still room for improvement. The testing involved various prompts across different domains, with results cross-checked by multiple AI systems.
- ▪Claude Opus 4.8 was tested against its predecessor, Opus 4.7, in a series of prompts designed to expose weaknesses.
- ▪The tests included coding, medical, finance, and legal scenarios to evaluate the models' responses.
- ▪Overall, Opus 4.8 showed improved honesty and calibration compared to Opus 4.7, despite a notable judgment error.
ZDNet files mainly under tech. We currently carry 486 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 | ZDNet |
| Canonical URL | https://www.zdnet.com/article/claude-opus-4-8-honesty-test/ |
| Publication time | Wed, 03 Jun 2026 01:07:00 GMT |
| Retrieval time | 2026-06-03T01:39:28.247Z |
| Last seen | 2026-06-03T01:39:28.247Z |
| 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 | NmtA-hapgsWh |
| 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
Innovation Home Innovation Artificial Intelligence I compared Claude Opus 4.8 with 4.7 in a 10-round honesty test - and a legal prompt broke it The latest models were pitted against coding, medical, finance, and legal traps, then I cross-checked the results with multiple AIs. Written by David Gewirtz, Senior Contributing EditorSenior Contributing Editor June 2, 2026 at 6:07 p.m. PT David Gewirtz/ZDNETFollow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways Claude Opus 4.8 handled uncertainty better than 4.7.Multiple AIs helped cross-check the test results.Even honest AIs can still rationalize bad assumptions.Last week, Anthropic released its latest frontier large language model, Claude Opus 4.8.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at ZDNet.