sameer

Woken up on a long haul flight to air hostesses hurriedly looking out the window. Turns out, the pilot announced to them that it's Aurora Borealis. Stared at it for a good 15 minutes and captured this beauty.

@JackWoth98 @antigravity congrats on the launch. excited to try this (especially the cli)

We are unifying our agentic surfaces to @antigravity 🚀 🔹 Antigravity 2.0 (desktop app) 🔹 Antigravity CLI 🔹 Antigravity SDK 🔹 Antigravity IDE One harness, wherever you need it. Read all the exciting news from I/O below 👇

a pre-requisite to influence is listening carefully and capturing intel. most folks miss this key step and get sub-par results.

the best thing we got out of @xai is the ability to search & retrieve obscure tweets.

@GergelyOrosz I've had the exact same issue and it's so annoying. Also, gemini cli usage has been nerfed pretty hard. Frustrating.

Another (real) story on how Google seems to hate paying customers: - Dev is a paying Antigravity customer - Wants to track usage. Antigravity doesn't provide a tool. - Uses CodexBar - Gets banned with Antigravity - "No problem, let me use Gemini CLI" - Gemini CLI also banned!!

this is the content I come to X for

@__rmrf @claudeai x.com/sameerbajaj/st…

@claudeai What about Claude Code?

We're bringing the advisor strategy to the Claude Platform. Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.

massive! I've had very good results using "/model opusplan" in claude code. opus for planning. sonnet for executing.

@clairevo @openclaw @steipete personality of a handbag... Hahaha I've been experiencing the same

ok it still has the personality of a sandbag but here are the @openclaw settings that fixed my gpt-5.4 reasoning leaks. @steipete provides the config, you just have to read the docs.

@jnnnthnn the onboarding is truly remarkable --well done! is there any way to setup a delete functionality on swipe? (for 'important' emails)

attention is all you have!

@willahmed 💪 strength before weakness. have both the Whoop and Oura now and really enjoying Whoops UX more.

You have no experience. You’ve never started a company. You’ve never had a full time job. Nike is going to kill you. You’re a kid. You don’t have technical skills. You shouldn’t build hardware. Apple is going to kill you. You can’t build hardware. You can’t measure heart rate non-invasively. Athletes don’t care about recovery. Under Armour is going to kill you. It won’t be accurate. You don’t listen. You’re an ineffective leader. You can’t recruit great talent. You’re going to have to pay every athlete. You can’t measure sleep non-invasively. It’s too expensive to research. Athletes are a small market. The product costs too much to make. The product costs too much to sell. Your valuation is too high. Consumers aren’t going to want it. Hardware is too hard. You should measure steps. Fitbit is going to kill you. You can’t build a marketing engine. You can’t raise enough money. You need a real CEO. Google is going to kill you. You can’t be a subscription. You can’t build a brand. You can’t do consumer in Boston. Your valuation is too high. You shouldn’t make accessories. You shouldn’t make apparel. Lululemon is going to kill you. You can’t predict Covid. Stay in your niche. You are going to run out of money. You can’t build a health platform. Amazon is going to kill you. You can’t measure blood pressure. You can’t get medical approvals. The market is too small. You don’t understand AI. The market is too competitive. It won’t work internationally. The supply chain is too complicated. You can’t build an AI. You can’t raise enough money. It’s too competitive. Healthcare isn’t going to want it. … Just keep going ✌️

What if your feed was Amjad Masad debating on product strategy, or Claire responding to Boris Cherny about AI That’s LennyFeed 🚀 An Agentic Social Feed with @lennysan guests No noise. Some hot takes. Like eavesdropping on the best product minds Try 👉 lennyfeed.com

@clairevo @morganlinton @openclaw curious - how so? have examples to share?

@morganlinton @openclaw Well over it x.com/clairevo/statu…

since no one else will say it: i'm on my way to spending $15-25k this year on my @openclaw agents

@myrrazor @petergyang codex is surprisingly good with nasty bugs in openclaw. Claude struggled for me.

@petergyang I actually use my Claude code to fix my OpenClaw whenever it breaks. Also Claude Code is more efficient with context so I use that as my coding driver but I do the planning and organizing with OpenClaw (which has context on everything that I’m doing all at once).

People who use both OpenClaw and Claude Code - what do you use each one for and why? Let us know in the replies. Really curious.

@petergyang CC: dev work and zero to 1 projects, new features etc Openclaw: remote investigations, browser automation and just about everything else. use the model opusplan. Unbeatable planning on claude code via opus 4.6 and execution via Sonnet.

highly recommend this browser cli. token usage is much lower and the CDP connection seems more stable. tried with both openclaw and claude code and it's seamless. install the skill that comes with it.

Finally launching an iOS app that I've been personally using for months and was sick of sideloading it weekly. Took me all day to create screenshots and launch on the App Store. And now, eagerly waiting for the review.

@0xZakk yeah, agreed. it's just how @steipete trained it to always bias towards action is what makes it different from Anthropic's recent updates

@sameerbajaj Setup and permissions are definitely still hurdles The big unlock with OpenClaw is agency - I don’t have to prompt it to do things if I don’t want to

Each new Anthropic release over the last couple of weeks has made me think they don’t understand why people use OpenClaw or why the people who are deep in it are excited about it

@ParvSondhi good take. but will kinda depend on what org they sit in. I would argue PMs have stronger tolerance for BS / org level influence to get things moving. Some designers struggle with that.

Hot take: Designers have more passion for craft and generally better taste than product managers and I’d bet cracked designers have a higher chance of being more dangerous with AI than PMs

Or you could click 1 button to sync this skill across different CLIs using this app