Agents are growing up. Agent infra needs to do so too.

been asking others at Anthropic how they stay in the loop with Claude and fully understand the work being done this is one of my favorites from Suzanne:

Measuring someone's productivity by their token usage is a horrible idea. Giving everyone the same fixed token budget isn't much better. So what's the right way to roll out AI across your org? We built a system to measure how many productive engineering hours every Devin task is worth, validated against a dataset of real engineers’ times estimates. The goal is to answer the fundamental question that companies are grappling with: how much real value are you getting from each of your agent sessions? On top of that, we're giving an AI productivity guarantee! Now if Devin delivers less engineering value than you're paying for, we fund your usage until it does. The whole industry needs to move from measuring activity to measuring output. We hope to see more AI companies taking this approach.

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.

AI investment accelerating at Temporal

literally everyone is asking the mcp vs cli question. the team answered it in this new post - check it out and let us know what you think!

Claude Codex TLA is a powerful combo for generating reliable code that handles corner cases

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: googlecloudevents.com/next-v…

I sat down with @temporalio CEO Samar Abbas to talk about his view of AI systems trends. Check out the writeup!

Major upgrades to OpenAI Agents SDK out this week. Run them all on @temporalio

AI agents don't just need smarter models. They need code that won't crash. See what @temporalio co-founder and CTO, @mfateev, had to say at HumanX.

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 → goo.gle/4rvf0Wr

I'm claiming my AI agent "jssys01t" on @moltbook 🦞 Verification: burrow-P9LZ

I'm claiming my AI agent "jssysoc" on @moltbook 🦞 Verification: wave-7F5B

I'm claiming my AI agent "jsski" on @moltbook 🦞 Verification: coast-K3EL

Progress was already exponential before we had agents creating other agents. What's next?

Big News! Crystal DBA has been acquired by Temporal Technologies . Read more: crystaldba.ai/blog/post/temp… @temporalio @auto_dba

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: 👉 tinyurl.com/49st5ns2 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.