Claude is quietly testing new limits - i checked 5 of my accounts | LAB 0028

Claude is quietly testing new limits on some accounts. SemiAnalysis says it's about 20% more on the five hour limit, but about 20% less over the month - great for sprints, worse if you use Claude all day every week. so i checked 5 of my Max accounts across 12 days. none of them are in the test. check yours in one session: in Claude go to settings (bottom left), then the usage tab. burn about 20 points off your five hour bar, then look at your weekly. if it moved about 5 points, that's normal. if it moved 6 or 7 or more, you're probably being tested. you can't trust a limit you can't see. also this week: Claude goes auto mode by default (i still run it with skip permissions), 1Password lets agents sign in without ever seeing your password, Grok Bot gets your phone apps, Anthropic used Claude to prove code can't crash, banks are catching AI agents in customer accounts, and Claude on the iPhone Duo. the practical - get grilled before you build. Matt Pocock's grill me skill makes Claude ask you three questions at a time, each with its recommended answer, before it builds anything. it finds the unknown unknowns. i asked it for a Threadify view made for the iPhone Duo's big inner screen and it found the problem i didn't know i had: the big screen was getting the cramped phone layout. links SemiAnalysis on the limits test: https://x.com/SemiAnalysis_/status/2113383965784502444 check your usage: https://claude.ai/settings/usage Claude goes auto mode by default: https://x.com/claudeai/status/2113360845409583307 1Password lets agents sign in: https://x.com/1Password/status/2113276767582498943 Grok Bot on your phone apps: https://x.com/bot/status/2113393684209176718 Anthropic: Claude proves code can't crash: https://x.com/AnthropicAI/status/2113390212911083894 banks catching AI agents (Axios): https://www.axios.com/2026/10/22/ai-agents-banks-unauthorized-accounts-access Robert Bye on Claude for the iPhone Duo: https://x.com/RobertJBye/status/2113414436648284432 Matt Pocock's grill me skill: https://x.com/mattpocockuk/status/2113196247964074322 chapters 0:00 Claude is quietly testing new limits 0:14 the limits test: check yours 2:26 Claude goes auto mode by default 3:29 1Password lets agents sign in 5:25 sponsor: Threadify 6:31 Claude proves code can't crash 7:40 banks are catching rogue AI agents 8:49 Claude on the iPhone Duo 10:03 get grilled before you build 13:11 see you next episode thanks to today's sponsor, my software Threadify - your lead generation agent for Threads, X and YouTube. see which posts bring you clicks and conversions, not just likes: https://www.threadify.app/home?utm_source=podcast&utm_medium=audio&utm_campaign=lab-0028&utm_content=sponsor&video_slug=lab-0028&cta_slot=podcast_description&entry_angle=whats_working want to sponsor a future episode? [e-mail]

What is Lenny’s AI Builders?

less scrolling. more “oh shit, i could use that.”

i’m Lennox. i dig through the AI updates worth your time, then test tools, models and agents on real work. what worked, what broke, and what you can try yourself.

for people making products, content and useful systems with AI. you don’t need to write code to build something worth using. grab the field notes for prompts, steps and the bits to watch out for: https://lennoxsaint.com/lab

this feed also keeps the earlier L E S S O N S episodes from my journey building with AI.