Most people open ChatGPT, fire off a prompt, get an OK answer, and move on. The thing that quietly separates the people getting incredible results from everyone else isn't a secret prompt — it's that they spent 5 minutes on Custom Instructions and never had to repeat themselves again. Custom Instructions sits in your settings. It's two text boxes ChatGPT reads silently before every reply, in every chat. Set it up once and the model already knows who you are and how you want to be answered. Here's the 5-minute setup that actually moves the needle: Box 1 — "What would you like ChatGPT to know about you?" Drop in three things: what you do, who you serve, and what you're working on right now. Example: "I run a SaaS business in customer support automation. My audience is small-business owners and marketing teams. I'm focused on growth and content right now." Skip hobbies and personal trivia — keep it work-focused. Box 2 — "How would you like ChatGPT to respond?" This is where most people leave money on the table. Tell it the tone, the format, and the things you don't want. Example: "Be direct and concise. Skip disclaimers and preambles. When I ask for copy, give me three variations. When I ask strategy questions, push back if my thinking is weak. Use plain English, not corporate-speak." Save it, open a new chat, ask the same question you've been asking for weeks. The difference is immediate. Two things to watch out for: don't stuff it with everything you can think of (the model weighs it heavier than you'd expect, and bloated instructions make answers worse not better), and revisit it every couple of months as your work shifts. What's in your Custom Instructions right now? Drop a line or two below — happy to suggest tweaks. Jason 🙌

OpenAI just released GPT-5.4… and it’s a pretty big step forward. If you’re using ChatGPT regularly, you’ll probably start noticing a few differences straight away. Here are a few highlights: 1. Much stronger at real workGPT-5.4 is designed for professional tasks like writing documents, building spreadsheets, analysing information, and producing structured outputs. In testing, it performed as well as or better than industry professionals in many knowledge-work tasks. 2. Better coding abilityIt now includes the coding strengths from the latest Codex models. That means stronger debugging, better code generation, and more reliable help when building apps, scripts, or automations. 3. Can work with tools and software more effectivelyOne of the biggest improvements is how it works with external tools, apps, and workflows. This is particularly important for AI agents that need to interact with websites, spreadsheets, APIs, and other systems. 4. Longer memory and contextThe model can handle extremely large inputs (up to 1 million tokens in some environments), which means it can process large documents, projects, or codebases much more effectively. 5. Better at searching the webGPT-5.4 is significantly stronger at deep research tasks where it needs to find and combine information from multiple sources. 6. Fewer factual mistakesOpenAI says responses are about 33% less likely to contain incorrect claims compared with the previous generation. What this means for us For most people in this community, the biggest benefits will be: • better prompts• more reliable outputs• stronger coding help • improved research• fewer hallucinations If you build workflows, automations, prompts, or AI tools, this release should make things noticeably smoother. Have you tried GPT-5.4 yet? What differences have you noticed so far? Chers Jason

How did everyone get on with ChatGPT over the last year? I’ve attached my stats, looks like use it a lot 😄

While looking to see if I had the GPT 5 yet (not yet apparently), I decided to look at the top GPT's on their discovery page and couldn't resist the Find My Celebrity Lookalike GPT. I'm not really sure about some of the matches, but it was definitely fun. I'm the top right.

"I think we're quite close to digital superintelligence (ASI). It may happen this year, maybe it doesn't happen this year, next year for sure." – Elon Musk What's ASI, Artificial SuperIntelligence? Think of it as AI that's smarter than any human at literally everything. Not just chess or math, but creativity, problem-solving, decision-making, the works. Why This Could Change Everything . . . 🚀 Science at Warp Speed: We're talking 100x faster breakthroughs in physics, chemistry, biology. Anthropic's CEO thinks we might even double human lifespan in the next decade. Imagine AI solving climate change, poverty, or aging itself. ⚡ The Winner-Take-All Moment Here's the kicker: DeepMind's Jeff Clune warns "the first ASI is likely to be the last ASI." Why? Because self-improving AI grows exponentially. First place becomes everything. This explains why Ilya Sutskever (OpenAI's former chief scientist) just raised $6B at a $32B valuation for his new company Safe Superintelligence (SSI)!! And get this, SSI has NO product yet. Top VCs like a16z, Alphabet, Nvidia, Sequoia, et.al. are betting he'll build the first (and last) aligned superintelligence. Recent Key ASI Developments This Week: 1. Meta creates Superintelligence Labs led by Scale AI and GitHub ex-CEOs as Zuckerberg escalates AI competition 2. Tesla achieves first fully autonomous car delivery from Austin factory to customer without human driver