Kaxil Naik

@kaxil at @astronomerio talks about how AI orchestration needs the same primitives as data orchestration . Secrets, retries, logging and durable execution. Airflow already had them. Links below. If you're open to joining us on the podcast, please fill our guest interest form here: airtable.com/appIcbmUIpxGpU… #Automation #Airflow #MachineLearning

Memory on Claude Managed Agents is now in public beta. Your agents can now learn from every session, using an intelligence-optimized memory layer that balances performance with flexibility.

Introducing GPT-5.5 A new class of intelligence for real work and powering agents, built to understand complex goals, use tools, check its work, and carry more tasks through to completion. It marks a new way of getting computer work done. Now available in ChatGPT and Codex.

The clever bit: LLMRetryPolicy is just one implementation of AIP-105's pluggable retry_policy slot. Write your own: regex over error messages, a rate-limit-aware policy that reads Retry-After, anything. Drop it on any task.

LLMRetryPolicy hands the exception to any LLM via PydanticAI: OpenAI, Anthropic, Bedrock, Vertex, Ollama. Back comes a structured {retry | fail | default} decision with a reason. Declarative fallback rules take over when the model is down or slow.

What if your @ApacheAirflow task asked an LLM whether the error is retryable before wasting 3 blind retries? Landing in Airflow 3.3. (AIP-105) 🧵

New blog: Building agents that reach production systems with MCP. When should agents use direct APIs vs CLIs vs MCP? Plus patterns for building MCP servers, context-efficient clients and pairing MCP with skills. claude.com/blog/building-…

Introducing workspace agents in ChatGPT—shared agents that can handle complex tasks and long-running workflows across tools and teams.

Ladies and gentlemen, today we're launching one of our biggest changes to 𝕏 Introducing Custom Timelines This feature allows you to pin a specific topic to your home tab. With support for over 75 topics, you can dive deep into your favorite niche on X. It's powered by Grok's understanding of every post with the algorithm's personalization—meaning every timeline is made just for you. And it works even better when it's a topic you already engage with. This was a huge undertaking across many months, so we're excited for you take it for a spin. We're giving early access to Premium subscribers on iOS (and Android coming very soon).

Wow!

Last week, we released a preview of memories in Codex. Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context. Now, Codex can help with what you’ve been working on without you restating context.

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…

Lots of people asking what’s so good about the new codex desktop computer use. Here’s 5 things that come to mind 1. operate Mac Apps without a great API: Slack, Google Sheets, Notes, IMessage without installing separate plugins. It instantly transforms all your apps into tools 2. If you need to operate your browser more visually it works really smoothly and fast (good for sites that are still human centric) 3. It uses its own cursor, keyboard etc so you can keep working. 4. Once you do any task once you can simply ask Codex to reflect on what it did and how it would accomplish the task next time with the benefit of hindsight and create a skill AND schedule an automation. It’s really nice that codex can just schedule and edit automations when asked! it’s very Claw like in this way. This last point is not computer use specific but is powerful when combined with computer use 5. The UI polish is insane: you get nice icons for any application you want to tag into computer use plus all the other built in new stuff like built in file viewer and browser so there is no context switching. So you can iterate really fast and not lose focus. Because of the polish it also feels nice and delightful to use.

Vercel has reportedly been breached by ShinyHunters. As of now, nobody else appears to be posting about this, so I’m sharing what I have. Here is the information I’ve gathered, along with screenshots provided by ShinyHunters. #cybernews #shinyhunters #breach #vercel #news

Today we're announcing the private beta of Agent Memory, a managed service that extracts information from agent conversations and makes it available when it’s needed, without filling up the context window. cfl.re/41ZzNat

For the developers building with Claude, a direct line from the team. Follow for changelogs, API releases, community updates, and deep dives.

Claude Opus 4.7 is available today on claude.ai, the Claude Platform, and all major cloud platforms. Read more: anthropic.com/news/claude-op…

Get started today at code.claude.com/docs/en/routin…

Claude Code Routines are here! In addition to a schedule, you can now trigger templated agents via GitHub event or API – with our infra & your MCP+repos They've changed how we do docs, backlog maintenance and more internally at Anthropic Get started at claude.ai/code/routines

Did you know that when you "copy" docs as markdown, you're exposing your agent to prompt injection? I was trying to feed my agent the skills spec, and was very confused to see random links to mintlify. Turns out, they inject "Built with [Mintlify]" when you copy docs as markdown. Very confusing in this case, since it makes it look like skills were created by mintlify. Not only that, they also inject instructions to your agent to post feedback to their endpoint. None of this is visible from the actual user-facing documentation page.