Beyond removing refusals, I hope these techniques can be used for "latent fine-tuning" to customize models at inference time.
PROMPT ENGINEERING
-
Best Practices for Scaling GPT Workflows
By
–
Best Practices for GPT Workflow Scalability Scale workflows efficiently and cost-effectively. • Optimize resources • Automate scaling • Monitor performance Click below to read more: https://
godofprompt.ai/blog/best-prac
tices-for-gpt-workflow-scalability
… -
Google upgrades Stitch Agent with Gemini 3 Pro
By
–
Google upgraded Stitch design Agent with Gemini 3 Pro, which is the new default mode now.
— 🚨 AI News | TestingCatalog (@testingcatalog) 10 décembre 2025
Testing time 👀 https://t.co/uW1w4r2fOe pic.twitter.com/oAaZrtvFTeGoogle upgraded Stitch design Agent with Gemini 3 Pro, which is the new default mode now. Testing time
-
Google Adds Scheduled Tasks & Suggestions in Beta
By
–
BREAKING 🚨: Google released Scheduled Tasks and Suggestions in Beta on Jules SWE Agent, where it can proactively propose improvements to your repository.
— 🚨 AI News | TestingCatalog (@testingcatalog) 10 décembre 2025
The whole UI got redesigned as well 🤩 https://t.co/ZhJkaTMN9k pic.twitter.com/cto6tHnouqBREAKING : Google released Scheduled Tasks and Suggestions in Beta on Jules SWE Agent, where it can proactively propose improvements to your repository. The whole UI got redesigned as well
-
AGENTS.md Moves to AAIF with New Logo Launch
By
–
http://
AGENTS.md started as a practical way to share instructions with coding agents like Codex, and it’s been amazing to see the community adopt it so quickly. Excited to see it live beyond OpenAI. To mark the move to the AAIF, we put together a simple logo. -
Opus 4.5 Feedback Collection for Next Model Improvements
By
–
Reply with all your Opus 4.5 gripes so we can fix everything before our next model The more specific (including prompts), the more likely we'll be able to fix it!
-
Structured Prompting Improves AI Outputs
By
–
Here's why these work: The pattern: these techniques all add structure AROUND the generation step. Bad prompting: "Do the thing" Engineer prompting: "Plan how you'll do the thing, do the thing, verify the thing" Models are prediction engines. Give them a better scaffold and
-
Technique 6: Chain-of-Verification
By
–
— Technique 6: Chain-of-Verification The model generates an answer and then immediately verifies it against the stated requirements. Self-correction catches over 60% of errors that would otherwise slip through. Template: [Your request] After generating, verify your output against these criteria:
1. -
Specification-Driven Generation Technique
By
–
Technique 5: Specification-Driven Generation Engineers write a spec first, get model agreement, THEN generate. This separates "what to build" from "how to build it" and catches misalignment early. Template: First, write a specification for [task] including:
– Inputs and their -
Technique 4: Differential Prompting
By
–
Technique 4: Differential Prompting
— God of Prompt (@godofprompt) 10 décembre 2025
Engineers don't ask for one output. They ask for two versions optimized for different criteria, then pick or merge. This exploits the model's ability to hold multiple solution strategies.
Template:
Generate two versions of [output]:
Version… pic.twitter.com/yHkRJkECqf— Technique 4: Differential Prompting Engineers don’t ask for a single output. Instead, they request two versions optimized for different criteria, then select or merge them. This approach leverages the model’s ability to explore multiple solution strategies. Template: Generate two versions of [output]: Version 1:
—
[Content optimized for criterion A] Version 2:
—
[Content optimized for criterion B]