I got the new GPT-5 pro API model to "Generate me an SVG of a pelican riding a bicycle". This pelican took 6m8s to generate and cost me $1.10!
PROMPT ENGINEERING
-
UI Testing Tools for AI Agents with Guardrails
By
–
Sweet UI for testing the agent – it highlights which bit of the flow is working. Other nice bits, Widget Builder, and Guardrails (still pings the model, but an easy to use way to do this) https://t.co/Q0jHhBaSI5 pic.twitter.com/nhGcnN7Waw
— Peter Gostev (@petergostev) 6 octobre 2025Sweet UI for testing the agent – it highlights which bit of the flow is working. Other nice bits, Widget Builder, and Guardrails (still pings the model, but an easy to use way to do this)
-
12 Essential ChatGPT Prompting Techniques for Better Results
By
–
Prompting isn’t about asking more, but asking smarter. Here are 12 must-know #ChatGPT techniques — from direct instructions to conditional scenarios and comparative analysis. The right prompt = better results.
Which one do you use most? #AI #PromptEngineering #ChatGPT -
17 Golden Rules for Writing Effective ChatGPT Prompts
By
–
Crafting prompts is an art These 17 Golden Rules for Writing ChatGPT Prompts show how clarity, structure & context make AI a true thought partner. Define the objective Assign a role Provide context Refine & repeat Prompting = the new digital literacy.
#AI -
Hyper Realism Photo Generation Pricing Model
By
–
About 5x more expensive, so I charge 5 credits instead of 1 credit for a photo for Hyper Realism
-
Vibe Coding: Process Issues Rather Than AI Problems
By
–
Maybe some of the big problems with vibe coding are process problems, not AI problems…
-
Training AI to truly understand your business
By
–
He publicado un episodio en @ivoox
: "Cómo entrenar a la IA para que entienda realmente tu negocio #podcast -
Claude 4.5 and GPT-5-Codex excel with accurate prompting techniques
By
–
I only stash them if they're accurate, but I find with Claude 4.5 and GPT-5-Codex and the right prompts they rarely make mistakes for me
-
OpenAI to unveil Agent Builder at DevDay
By
–
BREAKING 🚨: OpenAI is planning to announce Agent Builder on DevDay. Agent builder will let users build their agentic workflows, connect MCPs, ChatKit widgets and other tools.
— 🚨 AI News | TestingCatalog (@testingcatalog) 5 octobre 2025
This is one of the smoothest Agent builder canvases I've used so far.
The year of Agents 🤖 pic.twitter.com/BmSALOATGMBREAKING : OpenAI is planning to announce Agent Builder on DevDay. Agent builder will let users build their agentic workflows, connect MCPs, ChatKit widgets and other tools. This is one of the smoothest Agent builder canvases I've used so far. The year of Agents
-
Multiple Choice Questions as Model Training for Real-World Performance
By
–
What would be useful is when including more MC questions would also improve the answer performance on similar-topic questions where answer choices are not shown (like in a real world context). That being said I can see models who do well on MC settings being useful as verifiers