kisamoto
Joined 14 years ago
Karma
1,887
Submissions
368
Member since
Jul 16
Recent submissions
Comment · 3 days ago
I'm on a Workspace Pro subscription and the models I have are (in order of the dropdown on gemini.google.com):
- 3.6 Flash
- 3.8 Thinking
- 3.1 Pro
Back I go to the Antigravity pricing page and there is a tier "For Organisations". But now I have the option of either contacting sales (are you kidding me?) or "Start now via the API".
So I'm out - I want a simple subscription like Claude or Codex. I don't want API enterprise pricing for a 2 person organisation. I could use my personal account but I'm already paying increased Google Workspace prices to access Gemini and I can't even use the latest models with that.
If someone at Google sees this, flag this ridiculous behaviour please and get things under control. It should be a very clear process - don't show me things I can't access. Price things consistently and please just make things logical.
Comment · 1 month ago
In my opinion the OS should broker the communication between harnesses (which is part of Siri), LLMs and app functionality. It can take into account the permissions, the user could configure which LLM to use at an OS system settings level and complex workflows can integrate permissions like FaceID only once as the harness then interacts with APIs exposed by applications (arguably already there with app intents).
Self promotion blog article:
https://braw.dev/blog/2026-04-06-mobile-os-as-agentic-broker...
Comment · 2 months ago
Does this still apply if there are separate legal entities for US & EU operations? Take Hetzner as an example. They have a separate US company to deal with their US data center. Would their EU servers be vulnerable to the CLOUD Act?
Comment · 4 months ago
The irony to have the EU criticised for regulation on one side but complete government control of access on the other.
Comment · 4 months ago
> We focused on occupation-level shifts in remote work rather than personal choices, as decisions to work remotely may themselves reflect individuals’ mental health status
> Understanding remote work’s impact on mental health is important for workers deciding where to work
Remote work is not for everyone so if you are someone who predominantly makes their social connections in an office being forced to work remotely will have an impact.
However I think a lot who choose to work remotely have friends outside of work. I know this study focuses on those who live alone but it may also be very different for those who live with a partner/family/friends.
Anecdotally I have found that people who want social interaction in the office push for everyone in the office (rather selfishly in my opinion) because without enough people in - for example in a hybrid model - they don’t get the same kick.
Comment · 6 months ago
Zed - https://zed.dev/
Integrates a lot of agents (I use it with OpenRouter and directly with Pi) natively, is fast (you don't realise how laggy VSCode and its forks are).
Biggest disadvantage: lack of extensions. Lots of quality of life missing (e.g. gitignore integration to add/append gitignore files for different languages).
Comment · 6 months ago
It's worth considering why you are choosing a European stack.
Is it to support local/European companies - Great. Is it because you don't want to be at risk of the US and the CLOUD Act - Not so great. Any company that has servers in the US (which Hetzner and basically all CDNs do) are still vulnerable to the CLOUD Act and that includes servers in Europe.
Comment · 6 months ago
OP here. I do like Opus but I don't default to it for everything. My CC usage is a lot of Haiku/Sonnet and is also very bursty (bursts throughout the month, not a day).
I find that a lot of my Claude usage goes unused and then when I'm coding or leaning on agents I hit a limit and have to wait. I don't like that dynamic. I do have Extra Usage enabled (with a cap) but then I'm spending more than the $100 I already do.
I'm learning that a lot of people seem to consistently stay within limits and that works for them but I was looking for something different for myself.
The real pain is that Anthropic don't easily quantify usage (which can now change over the day). How many tokens is it? Minimum? Maximum? I tried to quantify this with OpenTelemetry for a while but have decided to move to this more flexible setup.
Comment · 6 months ago
A non-profit identity service.
Uses government IDs that a lot of people already have and saves signed credentials to your phone. There is a server element for the verification process but it runs all in-memory (follow the Mullvad model and not even have persistent storage in the servers).
It's fun. Get to practice mobile development (Flutter), use some local GPUs, learn about the changes to JWTs for signed, selective disclosure, Bitstrings for progressive disclosure lists etc.
Landing page is https://agora.gdn/ in case anyone wants to try a beta in the future.
Aspiring mountaineer.
[ my public key: https://keybase.io/ejones; my proof: https://keybase.io/ejones/sigs/em0zaIvNe2TeZ3vgjRwX3qUC1zJEcJmUSPqaYuaVm-E ]
Founder of carbonremoved.com to make CO₂ removal accessible to everyone.