I encountered my first run-in with an age verification prompt when I went to authenticate into the Claude iOS app. It asked me to use me iOS/iCloud account to confirm myage. It was quick and seamless enough, but even though I'm aware of this trend, it struck me as a bit jarring.
AWS actually hosts the models. Security & isolation is part of the proposed value proposition for people and organizations that need to care about that sort of stuff.
It also allows for consolidated billing, more control over usage, being able to switch between providers and models easily, and more.
I typically don’t use Bedrock, but when I have it’s been fine. You can even use Claude Code with a Bedrock API key if you prefer
I’ve been using Claude Code w/ bedrock for the last few weeks and it’s been pretty seamless. Only real friction is authenticating with AWS prior to a session.
thanks for the recommendations. it seems like i keep coming back to the basics of how i interact with LLMs and how they work to learn the new stuff. every time i think i understand, someone else explaining their approach usually makes me think again about how it all works.
trying my best to keep up with what and how to learn and threads like this are dense with good info. feel like I need an AI helper to schedule time for my youtube queue at this point!
I've been a mostly happy 1Password customer with a Family plan for quite some time. This may cause me to jump ship.
My biggest issue with 1Password has been 1) how intrusive it can be in the browser, especially on mobile when it's too proactive to show its dropdown and just gets in the way of my experience. I know this is challenging because a mobile device is a small screen, but it is incredibly frustrating. 2) how bad the Safari extension. It regularly fails to load at all.
Aside from that, while you're absolutely correct - 1Password is still relatively inexpensive, let's look at the improvements thet mention:
1. Automatic saving of logins and payment details
Isn't this what 1Password has always done or am I misunderstanding?
2. Enhanced Watchtower alerts
I haven't seen any of these alerts ever help me.
3. Faster, more secure device setup
This I have noticed. It is very convenient
4. AI-powered item naming
This is weak sauce. I don't care for "AI" to help me name my logins/accounts/etc.
5. Expanded recovery options
I'm not sure what this is and how it's different than what they've always offered on a Family plan.
I was buying a train ticket on Eurostar for my mother. I filled her name as the passenger. Scrolled down and used the 1Password data I have to fill my address and billing information. I proceed and pay. Later, when checking the ticket, I see it's on my name. 1Password changed the passenger details, and since the screen is small, I did not notice.
No 100% refund from Eurostar, but lesson learned.
I'm not leaving 1Password though. It's too convenient for my family.
I’ve had it do stuff like that and it’s very annoying when it’s an issue - which it sometimes is.
That and a lack of easy way to report a login page that doesn’t work perfectly would be my top annoyances (behind a 33% increase in a subscription that was already annoying me each time it came around).
“The workflow I’m going to describe has one core principle: never let Claude write code until you’ve reviewed and approved a written plan.”
I’m not sure we need to be this black and white about things. Speaking from the perspective of leading a dev team, I regularly have Claude Code take a chance at code without reviewing a plan. For example, small issues that I’ve written clear details about, Claude can go to town on those. I’ve never been on a team that didn’t have too many of these types of issues to address.
And, a team should have othee guards in place that validates that code before it gets merged somewhere important.
I don’t have to review every single decision one of my teammates is going to make, even those less experienced teammates, but I do prepare teammates with the proper tools (specs, documentation, etc) so they can make a best effort first attempt. This is how I treat Claude Code in a lot of scenarios.
Part 1 is linked in this article and explains a bit: “Minions are Stripe’s homegrown coding agents. They’re fully unattended and built to one-shot tasks. Over a thousand pull requests merged each week at Stripe are completely minion-produced, and while they’re human-reviewed, they contain no human-written code.”
I could be wrong, but my educated guess is that, like many companies, they have many low hanging fruit tasks that would never make it into a sprint or even somewhat larger tasks that are straight forward to define and implement in isolation.
I came here to ask this question. I find the existing agentic coding integraton to be clunky and slow. I've had much better luck with my Xcode projects just using my agentic coding tool of choice in the CLI.
reply