@Dimillian Pro tip: sort your recent chats by priority. And in priority mode (activity view), display your pinned threads.
You can find both options in the ellipsis menu next to “Recents” and “Priority” respectively
@Dimillian Pro tip: sort your recent chats by priority. And in priority mode (activity view), display your pinned threads.
You can find both options in the ellipsis menu next to “Recents” and “Priority” respectively
Notice that what I would not do is try to start a startup. Instead I'd build the foundation of knowledge to base a startup on later. Way better startup ideas would grow out of understanding LLMs deeply than trying to start companies based on what I knew at 17.
Another advantage of ChatGPT Work is that you can basically share a Codex chat!
I recommended ChatGPT Work to my wife, and a few minutes later she sent me a chat -- a fully agentic chat powered by the Codex harness that I could access on the web.
Can you imagine what could happen if it became a group chat? We’re moving toward a powerful multiplayer collaboration experience for friends, family, and colleagues. It’s going to be huge...
Another advantage of ChatGPT Work is that you can basically share a Codex chat!
I recommended ChatGPT Work to my wife, and a few minutes later she sent me a chat -- a fully agentic chat powered by the Codex harness that I could access on the web.
Can you imagine what could happen if it became a group chat? We’re moving toward a powerful multiplayer collaboration experience for friends, family, and colleagues. It’s going to be huge...
@koomen@morajabi I love and hate this at the same time 🤣 As someone who picked up the emdash habit after reading a lot of PG’s essays, I now feel obligated to write "--" instead of "—" so my writing doesn’t look AI-generated
@koomen@morajabi I love and hate this at the same time 🤣 As someone who picked up the emdash habit after reading a lot of PG’s essays, I now feel obligated to write "--" instead of "—" so my writing doesn’t look AI-generated
@_chenglou I was part of that team. Basically ChatGPT one year before it came out. Called LMChat and then another codename.
Google was too nervous to release it and DeepMind was blocked from shipping products that could disrupt Google.
I think about this a lot.
I’ve started using scheduled tasks in ChatGPT Work for personal automations. Despite the name, Work isn’t just for work -- it’s your own personal agent, powered by Codex and running on a computer in the cloud.
I use it for one-off and recurring tasks like:
- Monitoring a ticketing website so I don’t miss a concert when tickets go on sale
- Watching Craigslist for new listings and price changes while I look for a second dirt bike for friends and family
- Turning a noisy daily newsletter into a concise weekly summary
- Getting a weekend shortlist based on my interests and the weather in the Bay Area
- Checking parties in SF for a specific date when my brother is in town
- Keeping an eye on my finances
I used to run these automations on an always-on Mac mini using Codex desktop and remote access. Now I can create and edit them directly from my phone, and everything just works out of the box. I also use the Gmail plugin to receive email updates when needed.
Another advantage is that ChatGPT Work runs Codex in the cloud with access to my ChatGPT memories-- context that isn’t available when I run Codex locally. That’s especially useful for personalized tasks like my weekend shortlist.
To get started, open ChatGPT (web, desktop, or mobile), switch to Work mode, and describe what you want to automate. Chat for a minute to build up context, then ask ChatGPT to create a scheduled task. Note that the task will run using the model selected when it was created.
Enjoy your own personal AI agent!
"With GPT‑5.6, we’re introducing a new Max reasoning effort to give Sol the most time to reason deeply. Additionally, we’re introducing a new Ultra mode that goes beyond the capabilities of a single agent by leveraging subagents to accelerate complex work."
i am excited to see what will happen with tokenmaxxing startups, both for how they work internally and the products they can build.
openai offered to invest $2M in tokens into every startup in the current yc batch.
happy building!
"Codex isn't just for software teams. Everyone should use Codex agents. They are our teammates. Our superpowers to make us better than we were before. Better...smarter...faster." -- Jensen Huang
We tried a new thing with NVIDIA to roll out Codex across a whole company and it was awesome to see it work.
Let us know if you'd like to do it at your company!