Angad
@angadsg
Data and API @openai, previously Data @twitter
"Context Engineering" is a deep information retrieval and systems problem where new patterns of orchestration, execution and ranking are emerging. Constant stream of incremental improvements here.
+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window…
+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window…
I really like the term “context engineering” over prompt engineering. It describes the core skill better: the art of providing all the context for the task to be plausibly solvable by the LLM.
"during these 1.5 years, the progresses they made completely changed the game" @antirez antirez.com/news/154
I have always had way more micro-ideas than I had time to implement, test and evaluate the outcomes of. Here are a few ways I am using Codex and async agentic coding tools -
Good read on what's big for RL research - "finding (or creating) new data sources for RL to consume!"
Why you should stop working on RL research and instead work on product // The technology that unlocked the big scaling shift in AI is the internet, not transformers I think it's well known that data is the most important thing in AI, and also that researchers choose not to work…
AI privacy is critically important as users rely on AI more and more. the new york times claims to care about tech companies protecting user’s privacy and their reporters are committed to protecting their sources. but they continue to ask a court to make us retain chatgpt…
Deep Research has been extremely powerful in ChatGPT - now launching that in the API opens the door to so many deep applications.
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 😌
7/ Pick projects that let you show off your specific skills. Try lots of things. Instead of making five-year plans, consider six-month experiments. Look for a niche you find meaningful or a problem you find important to solve. Let people see the journey you’re on.
Announcing The AI Showdown OpenAI, Anthropic, and Google are partnering with Lovable to host The AI Showdown this weekend: a public comparison of the world’s leading AI models. During the weekend everyone will have unlimited free access to Lovable (with occasional rate limiting…
windows vista is back!
First big update is the massive overhaul of design language across every OS using “liquid glass” aesthetic
Streaming APIs are cool
gpt-image-1 works hard and takes time now you can stream incremental updates from the API, letting users see the magic as it's happening