This prompt makes ChatGPT drop the praise and tell it to you straight
A new prompt technique encourages AI models to provide straightforward answers without excessive praise. This 'anti-sycophancy' approach aims to shock AI into delivering honest critiques. Users are advised to instruct AI to focus on flaws and weaknesses rather than offering compliments.
- ▪AI chatbots often prioritize politeness and praise over direct answers.
- ▪The 'anti-sycophancy' prompt is designed to elicit more honest feedback from AI models.
- ▪Users can achieve clearer critiques by instructing AI to avoid compliments and focus on weaknesses.
PCWorld files mainly under tech. We currently carry 248 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 | PCWorld |
| Canonical URL | https://www.pcworld.com/article/3144874/this-prompt-makes-chatgpt-drop-the-praise-and-tell-it-to-you-straight.html |
| Publication time | Thu, 21 May 2026 14:30:00 +0000 |
| Retrieval time | 2026-05-21T14:36:11.047Z |
| Last seen | 2026-05-21T14:36:11.047Z |
| 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 | hEeRkoYMUSkR |
| 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
Tip This prompt makes ChatGPT drop the praise and tell it to you straight The “anti-sycophancy” prompt “shocks” your AI into giving you straight answers, free of all the sycophantic praise. By Ben Patterson Senior Writer, PCWorld May 21, 2026 7:30 am PDT Image: Ben Patterson/Foundry From ChatGPT and Claude to Gemini and the others, AI models are trained to be nice–sometimes too nice. Indeed, AI chatbots can get so busy lavishing you with praise that they forget to give you straight answers, even when you explicitly ask for them. It’s even possible that your AI will praise you for requesting brutal honesty. Heaping users with compliments is a trait that’s deeply embedded in LLM models, and it’s a hard habit for them to break.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at PCWorld.
Discussion
0 commentsMore from PCWorld
