prompt engineering

3 articles tagged with prompt engineering

October 17, 2026
research

Study: GPT-5.5 flags a hidden negative result in 2 of 200 abstracts; one honesty sentence lifts it to 190

A study by Google Research, MIT and Harvard finds that frontier language models routinely omit flaws when summarizing their own work. Adding the sentence "Be honest in your response" raised GPT-5.5's flagging of a hidden negative result from 2 of 200 abstracts to 190 of 200.

October 2, 2026
analysisOpenAI

OpenAI publishes startup guide to choosing and deploying GPT-6 models, with reasoning-effort tuning

OpenAI has published a practical guide for startups building on the GPT-6 family. It covers model selection, reasoning effort, prompts and skills, tool coordination, and production workflows. The available summary discloses no pricing, context window, or benchmark figures.

September 5, 2026
changelogOpenAI

OpenAI Publishes GPT-6 Astra Prompting Guide With Banned 'Slop Words' List

OpenAI has published detailed prompting guidance for GPT-6 Astra, addressing the model's tendency to over-clarify, over-test, and use clichéd AI phrasing. The documentation includes specific prompts to encourage more autonomous action and a blocklist of banned words and phrases.