
Working on AOSP-related things at @ActinisHQ. Leading the apps team at @GrapheneOS. Opinions are my own.
Estonia
Joined February 2014
- Tweets385
- Following108
- Followers41
- Likes8.3K
Could you extend it to Gmail app with non-gmail servers? I have ~dozen of boxes, and can use Gemini only for Gmail one.
Replying to @JorgeLiboreiro @BertuzLuca
It's just a rename to reduce confusion.
Given that it's omarchy, they can vibe-code it, I guess.
Cons: your files will be available to anyone else in the world because they're writing code, not reading 馃榾
Replying to @blur_vibe
Not necessarily. This time, it seems to be a bug - usage seems to have returned to normal. But yeah, next time it may be a product decision.
Replying to @alexandr_wang
also how it feels when you want to develop for muse (without breaking the ToS) and you can't test it in your unsupported region
Replying to @IntCyberDigest
So they did 0.00000001% of what AI labs do :) Anthropic even doesn't bother itself with rate-limiting, DDoSing websites.
Replying to @Muse
Is there a way to get dev access in an unsupported region (EU)?
Replying to @lydiahallie
Please fix usage limits first.
Then, multu-account in the desktop app would be great.
Replying to @plishman @theiaincameron
The first thing I thought about while reading this post 馃榾
Replying to @thsottiaux
Is there a PR size limit for codex code review on GitHub? Launched one 14 hours ago for a really big PR, it acknowledged but no result, and seems that you can't track it's status
Replying to @IndependentEco
I guess they use the same agency that asked influencers to post a Chinese foldable review on the foldable iPhone release day 馃榾
Kimi K3.1 Pro is the funniest scam ever. Bought a $200 sub to test; hit the 5h limit in 20 min. After that instructed the agent to NOT use subagents (why it's spawning unlimited subagents by default??) - 5h is still sad, but at least doesn't die in 20 min. Cancelled sub; will never buy again.
Replying to @suchenzang
It's in fact much more expensive than even Astra, at least on their plans.
Replying to @_MaxBlade
Yep. Same shit, even current OAI's limits are much better.
Replying to @Hesamation
K3.1 limits are a joke (and their harness seems to be quite bad).
Replying to @Kimi_Moonshot
Ran a code review task on the $199 plan with default settings; it consumed the 5h limit in 20 minutes and stopped, lol (default speed). Perhaps it used too many subagents, but it's still a problem: I didn't ask it to do that.