GPT 5.6 SOL IS HERE! How to use it.
In this episode I sit down with Dan Shipper to see how he runs his work and personal life on OpenAI's Codex Desktop with the 5.6 model. He walks through his card-based email setup, daily feeds for his company and Slack, and the in-app browser that lets his agent collaborate with him inside tools like Proof. We build a small SaaS app live, called Turnaround, and use it to explore why maintenance is the real product in the AI era and where Codex-native software heads next. Along the way Dan shares his pirates-versus-architects framing, his approach to fine-tuning a copy-editing model, and the patterns — pulses, Mailroom, and router threads — that hold his system together. The throughline: pick one simple win, let context do the heavy lifting, and manage the system instead of running every task by hand. Learn how to get customers with AI Agents: https://startup-ideas-pod.link/GTM-agents-IB Timestamps 00:00 – Intro 01:16 – Codex and GPT-5.6 Overview 03:40 – Training your own model: the step after skills 04:49 – Automating Email, Slack, Meeting Notes with GPT-5.6 08:53 – Why GPT-5.6 sharpens the results 10:26 – The light bulb moment with Codex 15:05 – Building Turnaround live: a maintenance badge 18:00 – GPT-5.6 vs. Fable: A tier and S-plus tier 19:34 – LFG and goal: looping toward a finished build 24:28 – Huge Opportunity: Codex-native apps 29:33 – The design checkpoint and the "warm paper" quirk 31:32 – Local models 34:04 – From 70% to 100%: pirates and architects 37:22 – Mailroom: giving Codex its own email address 40:58 – Getting started: download, grant access, explore 43:07 – Record and Replay: turning tasks into skills 44:37 – Closing Thoughts: Start small and build over time Key Points * Codex Desktop plus the 5.6 model runs as a full operating system for knowledge work — email, research, and building software from one surface. * Context is the multiplier: an agent wired into your computer and the web turns every inbox and feed into cards with a clear next action. * Maintenance is the real product in the AI era, now that anyone can one-shot a first version. * Codex-native SaaS — software you and your agent share inside the in-app browser — opens a fresh category with healthier margins. * A live build of Turnaround, a maintenance-status badge, reaches about 70% in one pass; an architect carries it the rest of the way. * Start with one simple win, grow the system over time, and let curiosity lead the way in. Numbered Section Summaries 1. Codex as an Operating System — I open by asking what listeners will take away, and Dan frames Codex Desktop plus 5.6 as his operating system for work. He favors the Desktop app over the CLI for its cleaner, more powerful feel, and credits OpenAI with refining the agent-on-your-computer paradigm. 2. The Card-Based Inbox — Dan shares his screen and shows Tend, an app that sweeps his inbox each day, summarizes every unread email, and drafts replies as cards with a next best action. I compare it to the way a 1960s executive once handled correspondence, now within reach for everyone. 3. Feeds, Context, and the In-App Browser — Dan pins threads for each part of his life, turning Slack messages and meeting notes into feeds that compound his preferences into revised prompts. The in-app browser carries full context into tools like Proof, which he calls the real unlock. 4. Building Turnaround Live — Together we build a small SaaS called Turnaround, a status badge that signals an app stays actively maintained. Using the compound-engineering plugin's LFG and Codex's goal command, the build reaches about 70% in one pass, complete with product forks and a design checkpoint. For the final visual polish, Dan would carry the design over to Claude and Opus before porting it back. 5. Getting Started and the Right Mindset — Dan's path in: download Codex, grant access to your computer, and ask it to propose tasks. He points to Chronicle and the Record and Replay plugin, and we close on the core mindset — manage the system, start with one simple win, and let curiosity lead over FOMO. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com/ LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND DAN ON SOCIAL X/Twitter: https://x.com/danshipper Youtube: https://www.youtube.com/@EveryInc/videos Every: https://every.to/
Read Video · 文字稿与深度分析
本集已有完整文字稿 + AI 深度分析
免费注册 · 无需信用卡 · 注册即获 150 积分,足够解锁本集
- 📄 完整文字稿含时间戳
- ✨ AI 摘要、关键词与思维导图
- 💡 核心要点与精彩引言
- 说话人 1
- 说话人 2
- 说话人 1
- 说话人 2
- 说话人 1
- 说话人 2
- 说话人 1
节目时间轴
Introduction to Codex with GPT-5.6 as an operating system for knowledge work and business.
- Dan Shipper argues Codex with GPT-5.6 is the ideal implementation of an AI agent for knowledge work, built after OpenAI observed the messy early paradigm of Claude Code and Claude Co-work.
- He rates GPT-5.6 as an A-tier model versus Fable's S+ tier, describing 5.6 as a Porsche that works for everything while Fable is so powerful and expensive it is only practical for ML engineers orchestrating agent fleets.
- Codex is positioned as an operating system for work, handling everything from email to writing to training custom models, with the key advantage being its in-app browser and access to full computer context.
Dan demonstrates his email and feed system built inside Codex.
- Dan built an app called Tend that scans his inbox daily, turns every unread email into a card with a summary and a drafted reply, and lets him iterate conversationally on each response.
- He maintains separate pinned threads for different life areas, such as a company feed that surfaces unseen Slack messages and meeting notes as cards with a next-best-action recommendation.
- The system compounds learnings over time by revising its own prompts based on what Dan liked, archived, or replied to, creating a feed policy that encodes what he cares about.
Why GPT-5.6 improves writing quality and how Codex functions as an operating system.
- Dan says GPT-5.5 was fine but not good enough, whereas 5.6 drafts emails that read as if he wrote them, makes far fewer mistakes, and is more careful about what it sends.
- The in-app browser is what makes Codex feel like an operating system, letting Dan plan his day in a markdown editor called Proof while Codex researches and edits in the same surface.
- Dan argues the model is only as powerful as the context you give it, and Codex's connection to the whole computer and internet is what makes it constantly useful.
关键概念
- Codex— OpenAI's agentic desktop app that Dan uses as his operating system for all knowledge work.
- GPT 5.6— The new model Dan considers the most usable and powerful for knowledge work and coding.
- agent-native SaaS— Software designed to be used inside Codex with your agent, which Dan sees as a massive business opportunity.
精选金句
I think the SAS apocalypse is so dumb because 99% of the world is going to want to use something that's maintained by someone else.
💡— Overturns the widespread assumption that AI will kill SaaS by arguing maintenance is the real moat.
I've actually found that I'm incredibly addicted to just like watching the stream, which I hate, but I just I just am like that for whatever reason.
🎯— A candid admission that even the expert can't stop watching AI work, revealing a hidden psychological trap of the agent era.
可执行的洞察
🛠️AI Tool Mastery
Codex with GPT 5.6 is an operating system for knowledge work, not just a coding tool.
Download Codex this week, give it access to your computer, and ask it to propose tasks it can do based on how you use your machine.
The model is only as powerful as the context you give it.
Set up one pinned thread in Codex for a recurring part of your life (email, company updates) and feed it context daily for a week.
💼Business Strategy
Agent-native SaaS designed for Codex has no token costs and normal software margins.
Identify one SaaS tool you use daily and sketch how it would work if built inside Codex's in-app browser.
People pay for maintenance, not the first version, since anyone can one-shot an app.
Add a public maintenance badge or status page to your product showing commit activity and bug fix turnaround times.
转录文字与 AI 洞察均由模型自动生成,可能存在少量误差。识别效果与音频质量、语速和发音清晰度相关——如有内容看起来不对,以原始音频为准。
播客与视频,已可阅读
音频播客

Scaling a $300K Moving Company in 60 Minutes
The Game with Alex Hormozi
2026年7月14日34:15EN
The Let Them Theory by Mel Robbins & Sawyer Robbins
Deep Dive Reads: Self-Help Book Reviews & Literary Insights for Growths
2026年3月26日22:08EN
How to Rewire Your Brain & Learn Faster | Dr. Michael Kilgard
Huberman Lab
2025年8月11日3:09:50EN
E250 为什么学了这么多知识,却还是做不好投资?
知行小酒馆
2026年9月4日1:40:38ZH-Hans
#24 Richard Löwenherz: Ich bin ein King - Holt mich hier raus!
Wer wir sind und warum das nicht klappte ...
2025年9月17日57:34DE
#482 - Bertrand Périer - Avocat - Devenir un génie de la prise de parole en public
Génération Do It Yourself
2025年7月20日2:43:59FR
视频

How To Force Your Brain To Be Motivated (when you don’t feel like it)
Daniel Pink
2025年10月28日7:25EN
Neuroscientist: You Will NEVER Feel Stressed Again | Andrew Huberman
RESPIRE
2023年2月27日11:05EN
No Priors Ep. 80 | With Andrej Karpathy from OpenAI and Tesla
No Priors: AI, Machine Learning, Tech, & Startups
2024年9月5日44:15EN
从「上瘾模型」到「专注力训练」,如何在被算法理解的世界里重新找回主动?| 英文访谈 S9E33
声动活泼
2025年10月16日50:48ZH-Hans
INDIA’S GOT LATENT S2 EP4 ft. Karan Aujla, Tanmay Bhat, Gurleen Pannu, Rahul Dua
Samay Raina
2026年8月2日53:54HI