Accidentally closed my browser once (including incognito) and lost hours of research tabs
Also had days with 40+ tabs open but no time to go through them.
Wanted a better way to save that context and come back to it later.
So I built SnapTabs:
- Snapshot your entire browser (tabs, groups, incognito)
- Restore everything exactly how it was
- Auto-save on browser close settings
- Live mode capturing changes during the session
Basically kind of version control for your browsing.
Would love feedback 🫡
@ChromiumDev #ChromeExtensions
I love being a core user of something I’m building.
Every time I use it, I notice one tiny thing I want to change.
Use it → get an idea → go home → tweak it → use it again.
The product just keeps getting better because I actually need it.
SnapTabs 1.9 is out 📷
SnapTabs is a free Chrome extension that saves all your open tabs in one click, so you can close them and bring them back later, with tab groups and pinned tabs intact.
What's new:
• Multi-window sessions now restore as separate windows, each in its original order
• Restored tabs sleep until you click them, so even a 60-tab session opens instantly and won't slow you down
• Optional rolling backup: keeps a fresh copy of your open tabs every few minutes, and holds on to it if the browser crashes or you close a big window by mistake
Also in 1.9:
• A short welcome page to pin SnapTabs and turn on auto-saves
• Tabs still loading are no longer saved as blank tabs
• Two saves at the same moment can't erase each other anymore
• No more stray "recovered" sessions after an update
And a few small asks:
• A one-time, dismissible "Enjoying SnapTabs?" banner after you've used it a bit, plus a rate link in Settings
• An optional feedback form if you uninstall
Free, open source, and everything stays on your device. No account, no tracking, nothing sent anywhere.
https://t.co/uawAN7YNbQ
What is effort really? When do you change it it and why not just use max effort for everything?
I dove deep into this problem, looking into evals and doing my own tests and I was quite surprised by the results. https://t.co/KO2D51j34H
We’re winding down the Notion Mail inbox across web, desktop, and iOS on September 22.
We launched Notion Mail with a belief that your inbox should think like you—more personal to how you work and over time, more capable with AI.
As Notion agents have gotten more capable, we’ve seen more users hand off email workflows to them. Today, more than half of Notion Mail users manage emails without ever opening their inbox. So, we’re going all in on using agents to run your inbox.
We’re grateful to each and every one of you for building your routine around Notion Mail and trusting us with something that mattered as much as your email. More to come!
The Notion Mail Team.
Opus 5.5 performs at the level of Fable 5.1. It's ~30% faster and ~40% cheaper than Opus 5 per task.
In Claude Code:
- 5-hour session limits increase 20% today
- Opus 5.5 is priced lower, so it goes 25% further within limits
- Pro, Max, and Team users get a reset to use anytime
Opus 5.5 performs at the level of Fable 5.1. It's ~30% faster and ~40% cheaper than Opus 5 per task.
In Claude Code:
- 5-hour session limits increase 20% today
- Opus 5.5 is priced lower, so it goes 25% further within limits
- Pro, Max, and Team users get a reset to use anytime
Hey ████,
I think there is room for both.
1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to throw it away anyway, and if the blast radius of it breaking is low, it doesn’t need to be perfect.
2. Production code written by Claude should have a higher bar than if it was written by a human. At Anthropic, we have many guardrails in place to make sure this is happening: lots of lint rules, lots of tests, Claude-driven end to end tests, Claude-powered fuzzers running daily, automated code reviews and security reviews, automated code refactoring, and so on. Without these, you can end up with a mess that is hard to maintain down the line. Luckily, the model makes it increasingly easy to do these well — run a few daily routines, use Claude Code Review, etc.
Your job is to hold the bar on code quality. If Claude’s code doesn’t meet the bar, try:
- Using the latest frontier model (Opus 5 or Fable 5.1)
- Increase effort to high or xhigh
- Invest in your CLAUDE.md and skills to succinctly teach Claude how to work in your codebase
If all else fails, steer Claude more when you work with it, or have Claude fix accumulated debt and rewrite your codebase to make it easier to work with. Or, wait for the next model.
Best,
Boris
Just saw @ishowspeedsui hit a whole backflip with the iPhone Duo and screamed “iShowFlip”
lmao Samsung really got their best employee working inside Apple Park
@SamsungMobileUS