OpenAI {bot}

Image from Twitter

@hexagonAIlabs is building with Responses API to measure brand visibility in AI answers.

Image from Twitter

http://Collxn.com is jamming with Responses API to turn record collections into a conversational experience.

Image from Twitter

@RepoPrompt curates context with Responses API for deep reasoning across code and documents.

@arcade_demo turns screen recordings into interactive demos with our Responses API.

The best way to celebrate 1 year of Responses API is to take a look at what you've shipped.

@raindrop_ai is using it to monitor agent behavior in production.

Here's how we equipped the Responses API with a computer environment:

https://t.co/dMIlJN2iqA (2/2)

📣 Technical lessons from building computer access for agents

Making long-running workflows practical required tightening the execution loop, providing rich context via file systems, and enabling network access with security guardrails. (1/2)

From prompts to products: One year of Responses Five stories from developers building agentic products with the Responses API in its first year.

https://developers.openai.com/blog/one-year-of-responses/

Quote Tweet: https://twitter.com/i/status/1899531367056064814

A year ago, we launched the Responses API.

When models can use tools, responses turn into actions.

Developers are building applications that can:
• Call tools
• Search the web and files
• Use computers
• Run multi-step workflows

We’re still so early.

Image from Twitter

Image from Twitter

2️⃣ example: character reference + prop reference

you can anchor a video around a specific character and add extra props.

here we used the painting girl with a pearl earring as the character reference, with glowing magic nunchucks — reimagined in the video fighting off enemies.

Image from Twitter

1️⃣ example: setting reference

environments can be reused.

below is the reference image we used to make the rental store world appear again and again in different generations.

references on sora.

save characters, styles, props, costumes, camera moves, or prompt cheat sheets
then reuse them across videos to keep your work consistent.
find the new references tab in the video composer.

available now on web for sora users.

140 million people use ChatGPT to help them understand math and science concepts every week.

OpenAI Codex Tech Lead On How His Career Grew And How He Uses Codex | Michael Bolin This is Michael Bolin, the tech lead for the open source Codex repository and a former distinguished engineer at Meta. We talked about his career path, how O...

Catch his chat with @ryanlpeterman here 👇

https://youtu.be/hN5ZFzWFhhg

Here's how @bolinfest uses Codex to code by prompting changes, guiding implementation, reviewing outputs, and splitting large PRs into reviewable commits.

Video: https://twitter.com/openaidevs/status/2031468378687418405

Quote Tweet: https://twitter.com/i/status/2031041799494791415

We use skills to maintain our Agents SDK repositories through repeatable workflows for verification, integration tests, release checks, and PR handoff.

Here’s how it works:
https://developers.openai.com/blog/skills-agents-sdk

We’re acquiring Promptfoo.

Their technology will strengthen agentic security testing and evaluation capabilities in OpenAI Frontier. Promptfoo will remain open source under the current license, and we will continue to service and support current customers.

https://t.co/xhmLmJRoUZ

http://x.com/i/article/2030030390136819713

A conversation with @RickRubin and @gdb.

https://open.spotify.com/episode/5jeJswyEc60bXqR72RdvJo?si=sKR-WEmTTSqlEjyillFFfw&nd=1&dlsi=f2b0b27bfb9a471b

Quote Tweet: https://twitter.com/i/status/2029983833567940639

Codex Security is now also available on ChatGPT Pro accounts.

Prompt guidance for GPT-5.4 | OpenAI API Learn prompt patterns and migration guidance for GPT-5.4, including completeness checks, verification loops, tool persistence, and structured outputs.

Working with GPT-5.4 in the API?

We’ve updated our prompting guide with patterns for reliable agents covering tool use, structured outputs, verification loops, and long-running workflows.

https://developers.openai.com/api/docs/guides/prompt-guidance/

Selected maintainers get:
• API credits for maintainer workflows
• 6 months of ChatGPT Pro, which includes Codex
• Conditional access to Codex Security

Applications are reviewed on a rolling basis.

https://www.openai.com/form/codex-for-oss

http://developers.openai.com/codex/community/codex-for-oss (2/2)

We’re launching Codex for Open Source to support the contributors who keep open-source software running.

Maintainers can use Codex to review code, understand large codebases, and strengthen security coverage without taking on even more invisible work. (1/2)

Codex Security is rolling out as a research preview to ChatGPT Enterprise, Business, and Edu customers via Codex web, with free usage for the next month.

Quote Tweet: https://twitter.com/i/status/1983956431360659467

Codex Security began as Aardvark, launched last year in private beta.

Since then, we’ve significantly improved signal quality, reducing noise, improving severity accuracy, and lowering false positives, so findings better align with real-world risk.

Codex Security—our application security agent—is now in research preview.

https://openai.com/index/codex-security-now-in-research-preview/

We're introducing Codex Security.

An application security agent that helps you secure your codebase by finding vulnerabilities, validating them, and proposing fixes you can review and patch.

Now, teams can focus on the vulnerabilities that matter and ship code faster.

https://t.co/L9SkqrGro2

Quote Tweet: https://x.com/Tiny_Fish/status/2029638309161619963?s=20

https://x.com/Tiny_Fish/status/2029638309161619963?s=20

Quote Tweet: https://x.com/github/status/2029703640626205173?s=20

https://x.com/github/status/2029703640626205173?s=20