Trevor Creech
@zedlander
member of technical staff @openai
I was looking for a fun weekend activity with kids and decided to vibe code this last night.. Turn your own photos into coloring pages that the kids can color on. Uses the latest @OpenAI image generation API. Early happiness results from my daughter seem to be 💯
this is a sick integration
We're excited to launch OpenAI's 4o image model in Playground today so you can make powerful edits to designs. We have a different spin on it: today we're launching 4 new tools for customers to change styles, colors, and put designs in mockups. In the coming weeks, we'll be…
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).
great distillation of what it's like to work here
Some reflections: calv.info/openai-reflect…
Launching today in the OpenAI API: - Deep Research in the Responses API! - Web search with o3/o4-mini! - Webhooks! - Logprobs in the Responses API! Please try to enjoy all of these ships equally 😌
And instead of polling, webhooks now let you receive notifications for certain API events—such as completed responses, fine-tuning jobs, and batch jobs. We recommend using webhooks for long-horizon tasks (like deep research!) to improve reliability. platform.openai.com/docs/guides/we…
agi will be delivered over webhooks platform.openai.com/docs/webhooks
also, here is one part that people not interested in the rest of the post might still be interested in:
congrats on the launch!
hey everyone! today we're launching the technical preview of @instantbots, build ai agents you can extend with hosted tools. you can use instant bot to: (1) build customizable ai agents (2) extend them with hosted tools. we host them for you as both REST API endpoints and MCP…
the last couple of GPT-4o updates have made the personality too sycophant-y and annoying (even though there are some very good parts of it), and we are working on fixes asap, some today and some this week. at some point will share our learnings from this, it's been interesting.
Image gen is now available in the API! We’re launching gpt-image-1, making ChatGPT’s powerful image generation capabilities available to developers worldwide starting today. ✅ More accurate, high fidelity images 🎨 Diverse visual styles ✏️ Precise image editing 🌎 Rich world…
it’s a great day to be a developer
beyond excited to release the gpt-4.1 family today! these models are really our love letter to developers: more of a focus on real world usage and utility, and less on benchmarks (although those turned out pretty great too).
many people worked on this, but @michpokrass really drove it. she is truly amazing, and one of the rare people who can do everything from deeply understand what users want to complex details of research and everything in between. although rare, these people make magic happen!
GPT-4.1 (and -mini and -nano) are now available in the API! these models are great at coding, instruction following, and long context (1 million tokens). benchmarks are strong, but we focused on real-world utility, and developers seem very happy. GPT-4.1 family is API-only.
TL;DR: we are excited to release a powerful new open-weight language model with reasoning in the coming months, and we want to talk to devs about how to make it maximally useful: openai.com/open-model-fee… we are excited to make this a very, very good model! __ we are planning to…
ok I hadn’t seen openai.fm until this morning and it’s pretty rad
o1-pro is live in the api! bring your hardest-hitting questions
o1-pro now available in API @benhylak @literallyhimmmm @shl @joshRnold @samgoodwin89 @byamadaro1013 @adonis_singh @alecvxyz @StonkyOli @gabrielchua_ @UltraRareAF @yukimasakiyu @theemao @curious_vii It uses more compute than o1 to provide consistently better responses. Available…