Founder @ Agents Mountain AI agents for real businesses - not demos. 15 yrs shipping SaaS. Now building agent-powered systems.
Poland
Joined November 2009
- Tweets375
- Following234
- Followers53
- Likes27
Giving API credits to the subscribers by @OpenAI and @AnthropicAI (not sure which one was first) is the smartest move to rapidly make huge amount of apps dependent on AI.
Still patching?
It's time to make your PHP app, a modern PHP app
axartmedia.com/php-upgrades
Is there any replacement excluding @zen_browser ?
We've decided to sunset Arc on December 22, 2026.
That's not an easy sentence to write. We spent years building Arc and celebrating each and every release along the way: we have so much pride and love for what we made alongside the Arc community.
Our priority is to deliver best-in-class security for our members. Keeping a browser secure takes constant, dedicated work that is only increasing in the age of AI. Dia was built from the ground up to meet today’s security standards, so that's where our engineering and security teams will focus moving forward.
We've worked to make switching to @diabrowser as easy as possible for Arc members. Here's how:
· Your passwords, bookmarks, extensions and history come over to Dia seamlessly.
· Spaces, Folders, and Tab Groups are in Dia and import over with your data intact.
· Dia now surpasses Arc benchmarks in stability, speed, and security.
· The browser features you use in Arc are free in Dia, and the AI is optional.
Thank you for using Arc, for pushing us to make it better, and for building alongside us. The team that made Arc is the same team behind Dia, and some of our most ambitious work is just ahead. We'd love for you to be there with us when it lands.
Yesterday, @claudeai Opus 5.5 was working on a feature in the background and casually closed every app on my Mac except @warpdotdev.
It ran a broad pkill command to stop one stuck process.
I asked it to build a feature. It killed my entire workspace.
Sep 26 AI Usage Value
$4.2k
5.41B Tokens
Claude █████████████ $2.2k
Codex ███████████ $2.0k
Claude 53.3%
Codex 46.7%
Based on @cc_usage
Swapped @claudeai Haiku for @typesafeai Jev as the judge in the pipeline that tags sentences.
8x faster: 3.4s → 0.42s per sentence
16x cheaper: $0.0084 → $0.0005 per sentence
Results are no worse.
Tabnax is FINALLY there!
After months testing different solutions for quick windows switching I decided to build my own.
Crazy fast.
Customizable.
MacOS native.
Switching windows has never been quicker!
Try it
github.com/danmartuszewski/t…
Claude Opus 5.5 looks very well after constatn use since the release.
It's fast.
It's token efficient.
It's smart.
It understands the intentions.
After few days, I can say more about @typesafeai Jev and the hype on it
- there is a lot fake/invalid demos that doesn't present Jev's real capabilities
- a lot of the things it does can be done with simpler classifiers
- It guarantees the correct output format not the the correct results
- In my real works text classification it's still not as reliable as Opus / GPT
- I still see a use cases for it and keep testing
I expected more things coming that sits somewhere between LLM and non LLM (programmatic solution), dressed (marketing) as new specified LLM type.
Happy time
Codex usage page finally refresh data in background!
chatgpt.com/codex/cloud/sett…
It already was the best tool I'm using in overall quality, and now with Studio Mode is even more amazing!
Thanks!
Aug 26 AI Usage Value
$5.0k
5.25B Tokens
Claude █████████████ $3.6k
Codex █████ $1.4k
Claude 72.0%
Codex 28.0%
Based on @cc_usage