this must feel insane

yeah it really is awful timing but if you don't want to use t3code or be forced to use it while still having great orchestration from any harness.. ruddr will always be here, choice is good :D

I tried the First Contact demo for the first time on my Quest 3 last year and it's really sad that basically nothing has the level of polish that older studios under Meta did, what a polished demo, that aged so well that I found no flaws on my Quest 3, almost 10 years later.

ruddr is a tool that lets your Codex or Claude Code spin up other instances of any model harness with any model, letting you set up model-agnostic workflows from any harness write your code with Claude Code, have it reviewed by Codex, just tell your agent to use ruddr CLI ruddr also has a pretty cool 'session viewer' for all your agents, (Factory Droid, Pi, Codex, Claude Code, OpenCode are all supported) so you can see all your sessions and their diffs and what changes were made all in one place LIVE! (EXTREMELY fast btw) I was tired of opening my IDE to view session-specific git diffs, it is now way easier, I can ask Opus 5.5 to spin up a GPT-6.1 Sol subagent using ruddr to review it's work, and your agent can even steer the agents spun up by ruddr and look at their progress live and provide additional context at anytime, and so can you with the ruddr TUI at anytime, including a live diff for every session, using ruddr or not :D Claude Opus 5.5 rewrote this entire project from Go + Bun to entirely in Rust in about 2 hours (besides the web dashboard which is TypeScript) with 5 subagents and one final review agent, before using ruddr itself to review it's work using GPT-6.1 Sol, below are the stats: TUI memory: 119 MB → 7 MB npm install: 512 MB, 174 packages → 18 MB, 1 package runtime: needed Bun → none binary: 6.5 MB → 18 MB (now includes the TUI, web dashboard, and agent adapters, MORE features than before)

Google AI Pro will get Deep Think soon!

buying a laptop made of magnesium so i can lick it to fall asleep

even if Gemini 4 is just good enough for general subagent usage, it's good enough to make a difference for data collection, Google will push this until it works, they have no other choice, dropping out of the AI race was never an option

it's not the only checkpoint, we got 3 iterations of Gemini Flash in a month, what makes you think we can't get atleast 1 a month for Argon? this is 100% intentional data collection in the Antigravity harness to improve their models, and it will most certainly pay off

Reminder that Google can infact wipe out marketshare whenever they want to, they just choose not to Now that generally capable models are coming to Antigravity that are known for efficiency and quality, and Google can collect data on them, I think Google could make a comeback

everything turns to slack

i should've just used pi instead of whatever the hell that was

if it's opus you'll be fine

ignoring how Sol got 6.7% better since launch just so nobody makes a six seven joke

@FactoryAI Droid? do it for the drama

Here you go! The Elder Scrolls III: Morrowind running natively on PS5.

thanks boss

so slick

wait till you find out this is the most retarded way to do this they are deadass running two games at once and doing some weird rendering technique to overlay spider-man in the batman game pure vibeslop instead of just porting the model and swinging behaviour to the batman game

there is a web version that uses @pierrecomputer diffs and trees i built right before going "rewrite in rust and use ratatui" and i'm glad i can just have both, so :D