introducing swarm: an experimental framework for building, orchestrating, and deploying multi-agent systems. ๐
shyamal
4,628 posts
Joined April 2019
- i'm hiring for a new team @OpenAI: Applied Evals our goal is to build the world's best evals for the economically valuable tasks our customers care about most. we'll execute as a group of highโtaste engineers, combining hands-on, unscalable efforts with systems that others can
- i love the openai team so much
- on my recent visit to india, i met a super sharp 19-year-old student from a remote town in gujarat, india. surprisingly, he traveled for 11 hrs each way to meet me for a 3 hr long discussion about agi, consciousness, creativity, anomalies in our approach to RL, spatial computing,
- we're still underestimating the profound impact of scaling test-time compute
- โฏ npm i -g @openai/codex โฏ codex โฏ codex -m gpt-5 -c model_reasoning_effort="high" codex CLI with gpt-5 is included in your @chatgpt plan!
- just three words x 3. 1: deep learning works. 2: time to build. 3: changes happen everywhere.
- feel the AGI
- exploring k-means clustering on the Iris dataset using code interpreter chatGPT plugin โจ
00:00 - OpenAI is nothing without its people
- oddly, over the past 2.5+ yrs at openai, there have been precisely three times when i really felt the magic (not counting dalle-2): the gpt-4 launch with chatgpt, deep research, and 4.5. ikyk







