It feels like Claude writes better in LaTeX than in Markdown or HTML. Can anyone confirm / contradict? I’m getting concise language, good argument development, and minimal LLM smell. Not my unusual experience. Using Opus 4.7 in Claude Code.
Today, we share a breakthrough on the planar unit distance problem, a famous open question first posed by Paul Erdős in 1946.
For nearly 80 years, mathematicians believed the best possible solutions looked roughly like square grids.
An OpenAI model has now disproved that belief, discovering an entirely new family of constructions that performs better.
This marks the first time AI has autonomously solved a prominent open problem central to a field of mathematics.
Agentic AI needs infrastructure that actually works in production. Today we're doubling down. 🚀
Welcoming Chkk and Adviser Labs to Temporal — two teams with AWS-scale distributed systems experience and Stanford AI research who were already building on Temporal before we ever called.
More at Replay next week👀
In the meantime, read more about this: https://t.co/EUR3Kj77ap
Agents fail in production for boring reasons. Transient API errors. Human approval steps that time out. Non-deterministic branching that nobody accounted for at 2am on a Saturday.
Our CTO @mfateev is at #GoogleCloudNext April 23 with @GitLab + @vellum_ai getting into the infrastructure decisions that determine whether your agent system survives contact with real users.
Register:
https://t.co/eYSw60GzEV
We're in the MS-DOS era of agentic AI. In this article, our CEO Samar Abbas unpacks what that actually means and what comes after: https://t.co/dTgOu9NPxB
Build long-running agents with more control over agent execution.
New capabilities in the Agents SDK:
• Run agents in controlled sandboxes
• Inspect and customize the open-source harness
• Control when memories are created and where they’re stored
Keep your AI agents running through process crashes and network drops. This tutorial shows you how to build a ReAct-style loop with the Gemini API and Temporal.
Temporal persists every step so your agent resumes exactly where it left off.
Learn more → https://t.co/AHoh5i9ne0
AI agents can prototype apps… But shipping real software takes hours of testing, debugging, and refactoring.
Agent 3 is 10× more autonomous — it keeps going where others get stuck.
The “Full Self-Driving” moment of software.
We've been building the pieces for years.
Projects, AI Agents, Automations.
Today, the dots connect.
Introducing 🧬 Taskade Genesis Preview
• One prompt → a full-stack AI app
• Powered by your Workspace
• Supercharged with GPT-5
Reply `Genesis` for early access 🚀
We’re excited to introduce RunLLM v2 today! 🎉
RunLLM v2 is rebuild of the product from the ground up focused on delivering the most powerful and flexible platform for enterprise support teams.
Read the RunLLM v2 launch blog post:
👉 https://t.co/biFZuylteZ
Today’s launch includes:
🤖 A new agentic planner with fine-grained reasoning and tool use support
✨ A redesigned new UI that enables creating, managing, and inspecting multiple agents
⚙️ A Python SDK that allows you to exercise fine-grained control over support workflows
We’ll be sharing more throughout the week, but today we’re focused on how RunLLM’s new agentic capabilities enable more precise answers and more effective debugging.