GPT 5: Our Current Use Cases (Ep. 530)

The team tees up a show focused on real GPT 5 use cases. They set expectations after a bumpy rollout, then plan to demo what works today, what breaks, and how to adapt your workflow.Key Points Discussed• GPT 5 launch notes, model switcher confusion, and usage limits. Plus users reportedly get 3,000 thinking interactions each week.• Early hands on coding with GPT 5 inside Lovable looked strong, then regressed. Gemini 2.5 Pro often served as the safety net to review plans before running code.• Sessions in code interpreter expire quickly, which can force repeat runs. This wastes tokens and time if you do not download artifacts immediately.• GPT 5 responds best to large, structured prompts. The group leans back into prompt engineering and shows a prompt optimizer to upgrade inputs before running big tasks.• Demos include a one shot HTML Chicken Invaders style game and an ear training app for pitch recognition, both downloadable as simple HTML files.• Connectors shine. Using SharePoint and Drive connectors, GPT 5 can compare PDFs against large CSVs and cut reconciliation from hours per week to minutes.• Data posture matters. Teams accounts in ChatGPT help with governance. Claude’s MCP offers flexibility for power users, but risk tolerance and industry type should guide choices.• For deeper app work, consider moving from Lovable to an IDE like Cursor or Cloud Code. You get better control, planning, and speed with agent assist inside the editor.• Gemini Advanced stores outputs to Drive, which helps with file persistence. That can outperform short lived code interpreter sessions for some workflows.• Big takeaway. Match the tool to the task, write explicit prompts, and keep a second model handy to audit plans before you execute.Timestamps & Topics00:00:00 🎙️ Cold open and narrative intro02:18 🗓️ Show setup and date, who is on the panel02:43 🧭 Today’s theme, GPT 5 use cases and rollout recap05:39 🧑‍💻 Lovable coding with GPT 5, early promise and failures07:44 🧪 Switching to Gemini 2.5 Pro as a plan validator09:55 ❓ GPT 5 selection disappears in Lovable, support questions10:08 🔁 Hand off to panel, shared issues and lessons10:08 to 13:38 🧵 Why conversational back and forth stalls, need for structure13:38 ⏳ Code interpreter sessions expiring quickly15:00 🧱 Prompt discipline and optimizer tools16:54 💸 Theory on routing and cost control, impact on power users19:45 🔀 Model switcher has history, why expectations diverge20:48 👥 GPT for mass users versus needs of power users23:19 ⚙️ Legacy models toggle and model choice for advanced work25:04 🧩 Following OpenAI’s prompting guide improves results27:10 🔧 Prompt optimizer walkthrough29:31 🐔 Game demo, one shot HTML build and light refinements31:13 💾 Persistence of generated apps and downloads32:42 🔗 Connectors demo, PDFs versus CSVs at scale34:58 ⏱️ Time savings, hours down to minutes with automation36:43 🛡️ Data security, ChatGPT Teams, and governance39:49 🚫 Clarifying not Microsoft Teams, Claude MCP option41:20 🗺️ Taxonomy visualizer and chat history exploration45:36 📉 CSV output gaps and reality checks on claims47:30 🧭 UI sketch for a better explorer, modes and navigation48:47 🛠️ Advice to move to Cursor or Cloud Code for control52:49 📚 Learning path suggestion for non engineers55:42 🎼 Ear training app demo and levels59:07 🔄 Gemini versus GPT 5 for coding and persistence60:30 🗂️ Gemini Advanced saves files to Drive automatically63:06 🧳 Storage tiers, Notebook LM, and bundled benefits64:18 🌺 Closing, weekend plans, and community inviteThe Daily AI Show Co-Hosts: Andy Halliday, Beth Lyons, Brian Maucere, Eran Malloch, Jyunmi Hatcher, and Karl Yeh