开启时会模糊预览图，关闭后正常显示
Memory is a key primitive for “continual learning” —> basically how does your agent learn with you over time Great walkthrough from @RLanceMartin with DeepAgents on -how memory is updated over time explicitly and implicitly - how skills are learned and stored for future agents to use - the research papers that led to these blocks - how to combine continual learning with Agent Observability, basically store your traces so you can learn from them later
agents, harnesses, and evals @LangChainAI, prev @awscloud, phd cs @ temple
Check it out on Tailwind Plus here 👉🏻 https://t.co/N1002KKD49 Going to put together a little video demo showing how it all works soon!
Creator of @tailwindcss. Listener of Slayer. Austin 3:16.
Last week, a security researcher using our previous model found and disclosed a vulnerability in React that could lead to source code exposure. I believe these models will be a net win for cybersecurity, but we are in the 'real impact phase' as they improve.
We are beginning to explore trusted-access programs for defensive cybersecurity work.
Just shipped Oatmeal — our first multi-theme marketing site kit for Tailwind Plus 🥣 Multiple color and font options, and a big collection of highly composable elements that you can piece together into exactly the site you need.
Check it out on Tailwind Plus here 👉🏻 https://t.co/N1002KKD49 Going to put together a little video demo showing how it all works soon!
GPT-5.2-Codex launches today. It is trained specifically for agentic coding and terminal use, and people at OpenAI have been having great success with it.
AI is cool i guess
RT @Sirupsen: An incredible year for turbopuffer is closing. We now manage trillions of vectors and tens of petabytes. We’ve puffed up reve…
Choose disfavour where obedience does not bring honour. I do math. And was once asked by R. Morris Sr. : "For whom?" @halvarflake@mastodon.social