> Does JJ really prefer for me to think backwards?
Perhaps it’s the other way around. I have a standard agentic instruction to summarize prompt instructions using jj describe. After it makes changes I can see both the file changes made and a log description of what prompted those changes. When done it’s just jj new and its ready for the next set of prompts.
I wonder about a scheme using public key encryption where a scannable code (public key of the pair) is displayed on the log-in screen, where one has an app on a phone that can match it and send an authorization to the site for login.
Moves the complexity to unlocking a phone and starting an app.
In Denmark the official identification app does basically this. When you to officially verify yourself for e.g. the bank, government sites or whatever you type a “username” (identity string that officially should not be linkable to you but in practice often is). The site then displays a QR code that you scan with phone and then approve with a slider. It is not perfect but it is fairly easy for everybody.
I wonder about a scheme using public key encryption where a scannable code is displayed on the log-in screen, where one has an app on a phone that can match it and send an authorization to the site for login.
Moves the complexity to unlocking a phone and starting an app.
In Denmark the official identification app does basically this. When you to officially verify yourself for e.g. the bank, government sites or whatever you type a “username” (identity string that officially should not be linkable to you but in practice often is). The site then displays a QR code that you scan with phone and then approve with a slider. It is not perfect but it is fairly easy for everybody.
I assume this scannable code would be a QR code. I still regularly see QR codes throw older people for a loop, even if I know they’ve used them before. Opening the camera app to login is not a natural thing to do.
It also assumes everyone has a smart phone. Maybe this true, but it becomes less true the older someone gets.
Honestly… just paste my comment into the prompt and you’ll get it 80% of the way there. The important thing is to seed it with instructions so it will iteratively improve its own instructions each session.
Did you modify the Plus plans usage recently or as part of this introduction? Given that Pro plans usage are multiples of it (5x/20x) and given reports of less Plus usage, clarification would be appreciated?
Transparency on this sort of thing is the best way to address negative company sentiment.
I'm honestly not sure, as I don't work on it. My understanding from afar is:
- There was a 2x promotion in March that ended on April 2, so limits have felt tighter since then
- We sometimes reset rate limits after bugs or milestones or because Tibo feels generous, which can make some days feel different than others (they are typically announced here: https://x.com/thsottiaux)
- Recently Plus was tweaked to have a smaller 5h limit but an increased weekly limit
- Lastly, as part of the new Pro launch, the $100 & $200 Pro tiers are getting a 2x promotion, meaning they are temporarily 10x/40x instead of 5x/20x
I've asked our team to clarify the pricing page. Agree it's not clear.
> “Earendil is a venture-backed for-profit, public benefit corporation” - Ronacher
The author favors the “public benefit” part, but less so the “venture-backed for-profit” part, is my speculation. Likely the reason for the disapproval of the finance types and the title “I’ve sold out”.
Their web site left me with a bad taste. I want to like them but… No front page pricing. Popups obscuring screen, with no options I agree with. Standard safari shows blank page for products. Cute images that overwhelm content. How many sign up for free prompts are enough?
You (are required to) treat your code as having to fulfill both functional requirements and declared non-functional requirements, including measures of maintainability, reliability, performance, and security and (regulatory/legal) compliance.
Perhaps it’s the other way around. I have a standard agentic instruction to summarize prompt instructions using jj describe. After it makes changes I can see both the file changes made and a log description of what prompted those changes. When done it’s just jj new and its ready for the next set of prompts.
reply