The OpenAI cookbook is the top trending repo on Github this month!
If you haven’t checked it out, it’s an incredible resource for getting started on the API — maintained by our team (and others!)
github.com/openai/openai-…
Sherwin Wu
1,554 posts
- We just open sourced our tokenizer! This should help all users of our API better understand their usage. It's also incredibly fast – 3-6x faster than other open source alternatives!
- My top use case for GPT-4o native image output right now: using it to imagine home reno projects in our new place. i.e. look at this potential built-in bookshelf / reading bench — rendered in one shot!
- Overheard from a YC founder: "Whenever a new frontier model comes out, a subset of the batch's products just start working and they takeoff. Many of us are keeping burn rate low, kind of just waiting" Hoping that o3-mini unlocked the takeoff moment for some startups last week!Update: this actually ended up working out. Very, very impressed with my initial o3 mini (high) experience.
- In case it isn’t clear: all of our services (i.e. our API and ChatGPT) are still being actively maintained and monitored. Folks have actually stepped up to ensure duplicate on-call coverage during this time to make sure the customer experience is still stable and reliable.A note to @OpenAI developers 🫶: I wanted to express my appreciation for all the warm, thoughtful, and supportive messages I got and I’ve seen posted across the community. Despite a moment of uncertainty, our commitment to developers remained steadfast. In the meantime,
- We just launched the official OpenAI Agents SDK! Inspired by our Swarm SDK, @_rohanmehta, @stevenheidel, and @jamesmhills evolved it into an even more powerful framework that's a delight to use. We think you'll love using it!
- We're launching the ChatGPT API and the Whisper API today. The ChatGPT API is 10x (!!) cheaper than our current davinci models – with no loss in performance. Happy building! openai.com/blog/introduci…
- First time o3 (full, not mini) is available to users outside OpenAI – and it's wrapped in a really slick product experienceReplying to @OpenAIPowered by a version of OpenAI o3 optimized for web browsing and python analysis, deep research uses reasoning to intelligently and extensively browse text, images, and PDFs across the internet. openai.com/index/introduc…
- Don't sleep on gpt-realtime-mini – a 70% cheaper version of the full-size model. This should make many voice workflows cheap enough to deploy widely. But the real surprise: our internal qualitative testing has it scoring higher than even gpt-realtime (!) for voice quality.
- We're hiring Forward Deployed Engineers (FDEs)! If you're a software engineer who loves working directly with customers and helping them tap into the power of frontier AI models – DM me with an example of something cool you've built on top of our API. openai.com/careers/forwar…
- :froge_heart_openai:i love the openai team so much
- The fun part about this whole thing coinciding with the birth of your first child is that when people ping you at 2am to sign a letter, you’re already up in the hospital room changing a diaper 🙃Now 715. I should note that this includes colleagues with tenuous visa situations, a colleague who was literally in the hospital with the birth of their first child, signatories in the air on their way to Thanksgiving break, and many others. The support here was shocking
- Shipping every week! We just open-sourced Point·E – a model that outputs 3D point cloud models. Does in 1-2 minutes what would previously take hours!
