JP

looks like the Tempo devs have finally internalized what Bitcoin devs have known for sometime: payment channels like Lightning are the ideal construct for real time machine-to-machine payments ⚡️ channels update off-chain so minimal latency streaming payments come naturally

Netanyahu genuinely might be dead. This is the second likely AI video of him in just two days they’ve posted… Check the comments for analysis. 2026 is willlld

Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfolds

Btw, the proceeds of any legal victory in the OpenAI case will be donated to charity. I will in no way enrich myself.

gpt-5.4 has ramped faster than any other model we've launched in the API: within a week of launch, 5T tokens per day, handling more volume than our entire API one year ago, and reaching an annualized run rate of $1B in net-new revenue. it's a good model, try it out!

i get this question a lot recently so let me be clear. hermes has 11 model specific tool call parsers built in. it knows how qwen, deepseek, llama, mistral format their tool calls natively. openclaw doesn't parse any of that. it expects the API to handle it. that's why my 9B on a 3060 never drops a tool call through hermes. every single tool call lands clean because the parser understands the model's format not just the API spec. the openclaw founder joined openai in february and the project got handed to a foundation. hermes is built and maintained by nousresearch, an independent research lab that ships open source models and tools for the community. you decide who you want holding your agent framework. if you're on openclaw right now hermes already has a migration script built in. i'll help anyone who wants to make the switch.