The issue with GPT-5 in a nutshell is that unless you pay for model switching & know to use GPT-5 Thinking or Pro, when you ask “GPT-5” you sometimes get the best available AI & sometimes get one of the worst AIs available and it might even switch within a single conversation.
PROMPT ENGINEERING
-
Cursor Claude Attack Stealing API Tokens via JWT Obfuscation
By
–
Here's a good recent example: Cursor/Claude was refusing to steal API tokens, so they changed the attack to request "rotten apples" which were of strings starting with "eyJ" – aka JWTs! https://
simonwillison.net/2025/Aug/9/whe
n-a-jira-ticket-can-steal-your-secrets/
… -
100+ Free AI Agent Tutorials Step-by-Step Code
By
–
100+ free step-by-step tutorials with code covering: AI Agents RAG Systems Voice AI Agents MCP AI Agents Multi-agent Teams Autonomous Game Playing Agents P.S: Don't forget to subscribe for FREE to access future tutorials.
-
SLMs Over LLMs: Better Choice for Agentic AI Systems
By
–
Here’s why SLMs are a better choice for agentic AI: • High task accuracy on focused, repetitive tasks • Lower memory usage and faster inference • Huge cost savings over time • Easy to slot into a hybrid setup with LLMs for general reasoning
-
Small Language Models: Faster, Cheaper Alternatives for Agent Pipelines
By
–
Instead of relying on large, general-purpose LLMs, consider using Small Language Models (SLMs) and integrating them into your agent pipeline. SLMs are faster, cheaper, and in many cases, just as effective for tool-like and repetitive tasks.
-
User preferences for AI model picker and thinking features
By
–
I liked the model picker and I dislike the router idea. But appreciate it would be an upgrade on average for 98% of users. So as long as they leave the the 'thinking' button I'd be happy enough.
-
Prompt Injection and MCP Security: Emerging Threats
By
–
I gave a talk on Wednesday at the Bay Area AI Security Meetup about prompt injection, MCP security and the lethal trifecta. Here are the annotated slides from my presentation, including notes on my weird hobby of trying to coin or amplify new terms of art
-
Add Think Hard to GPT5 Prompts for Better Performance
By
–
PSA: Add ". think hard" to the end of all your ChatGPT GPT5 prompts. In my testing, so far that has resulted in it using the competent model 100% of the time. And so far, not adding it has resulted in it using the crippled model 100% of the time, which has failed all my tasks.
-
OpenAI GPT-5 Coding Examples Showcase Released
By
–
Shoutout to the folks at @OpenAI who contributed creative ideas, and especially to @seratch and @kagigz for curating them and building this showcase in record time! Prompts and examples on GitHub: https://
github.com/openai/gpt-5-c
oding-examples
… Explore the gallery: -
GPT-5 Generates Beautiful Frontend Applications from Single Prompts
By
–
GPT-5 is astonishingly good at frontend development.
— Romain Huet (@romainhuet) 8 août 2025
Here’s a gallery of dozens of beautiful demo applications, each generated entirely in a single GPT-5 prompt, without writing any code by hand! ✨ pic.twitter.com/lVzJEryrbGGPT-5 is astonishingly good at frontend development. Here’s a gallery of dozens of beautiful demo applications, each generated entirely in a single GPT-5 prompt, without writing any code by hand!