so... I built the thing type-safe AI for handling Slack messages. powered by @typesafeai's model Jev 1.13
Awaits publication! But you can check how it works below ⤵️
https://t.co/VwPLfQVy1i
@Hassan4_s Codex (GPT 6 Astra) & Claude (Opus 5.5); Codex did the hard things like applying the exploit (kudos to chris-ritsen on GH) & organizing the systemd service to kill the bloatware processes on reboot;
opus did the custom launcher and all UI (was blocked by the guardrails)
Over the weekend I've rebuilt the whole Tizen 6.5 experience on my 4-years old smart TV.
Removed 49 Samsung background processes (most "smart" addons / tracking software, way less CPU & memory usage), revamped the home screen (boots in no-time and is way more responsive), remapped TV remote keys, added Home Assistant integration and custom popup (invoked via old Bixby button) to control my living room through HA integration.
crazy times. normally it would take me few weeks of research and work. This was done in just one day.
@kxnstandin yes. Used the research shared by chris-ritsen (check github). My model wasn't listed, but Codex managed to re-use the research to support it. Also managed to preserve the root permissions over the reboots (to kill the bloatware-processes)
We keep improving performance across Claude, and you may have noticed it starts responding sooner!
Claude Code now gzips the conversation it sends on every turn, so it reaches the model faster. Cloud sessions also start up as soon as you start typing.
Github still does not have image preview in PRs, so we built our own https://t.co/MvxQE9JUTx
no tracking, just a simple JS snippet for enabling the gallery. thank me later thx
I made $0 in September 2026.
🤼 https://t.co/VwPLfQW5QQ – $0/MRR
🏢 https://t.co/Gy1nfzhX0o – $0/MRR
🌉 https://t.co/R68tRkftiK – $0/MRR
...all waiting for the Atlassian / Slack reviews! yikes