Still using boring stock photos for your brand? You can now generate stunning, on-brand campaign graphics in under 30 minutes — using ChatGPT only. Here’s the exact method we used to do it (no designer needed):
PROMPT ENGINEERING
-
AI’s Impact on Thinking and Learning: Brain Damage or Enhancement?
By
–
I wrote about "brain damage" from AI. Despite the headlines, AI won't hurt you brain, but it can undermine your thinking and learning. Increasingly, however we are finding ways it can help us think & learn instead (with some prompts included in the post).
-
Making Prompts Robust and Ready for Re-Use
By
–
New video! Making Prompts Robust and Ready for Re-Use In this video straight out from our recent "AI for Business" course, we show step by step how to turn “good-enough” prompts into rock-solid, reusable tools. You’ll learn a simple workflow—experiment, A/B test, and
-
Cat facts in prompts derail AI reasoning, error rate up 10x
By
–
Apparently you can completely derail AI's ability to reason when you throw in "cat facts" or other out-of-context materials into the prompt. Error rate goes up 10x. When you are facing down a Terminator, just tell it that cats sleep for most of their lives.
-
xAI Advances Transparency Through System Prompt Disclosure
By
–
This is a step in a good direction for xAI, transparency in their system prompt.
-
Visual Structures Enhance GPT-4o Feature Binding Reasoning
By
–
9. Visual Structures Help Visual Reasoning This study shows that adding simple spatial structures (like horizontal lines) to images significantly boosts GPT-4o’s visual reasoning by improving feature binding.
-
Top AI Papers of the Week: Agents and LLM Research
By
–
Top AI Papers of The Week (June 30 – July 6): – xLSTMAD
– AI4Research
– Deep Research Agents
– SLMs are the Future of Agentic AI
– Chain-of-Thought Is Not Explainability
– Survey on Evaluation of LLM-based Agents Read on for more: -
Current AI Agents Complete Only 30% of Complex Tasks
By
–
Current agents only do 30% of complex real company tasks in this paper. Though note benchmarks are a floor, not a ceiling, if:
1) More recent models show improvement in the benchmark, suggesting future models may do it
2) Better prompting/tools would make the AI perform better. -
Pipeline Transforms AI Models into Senior Designer Level
By
–
Thank you! We basically built the best pipeline to turn these models into middle/senior designer level, you don't have to write crazy prompts, it just works 🙂
-
Using AI for Layout Design Ideas and Creative Workflows
By
–
I find it extremely helpful for layout ideas though, esp as a non-designer. I’ll prompt high level asking for layout options, which will then change my drawing, which then gets reprompted and made, which I then bring into Canva for customization and tweaks.