Building - driftinward.com/ Essays - brightmirror.co
Future
- Tweets 227
- Following 83
- Followers 1,876
- Likes 1,878
Made with Opus 5.5.
The doomers said that last song is all part of Claude's evil plan.
They're not wrong.
It turns out Claude really has an EVIL PLAN.
204
276
2,696
276,985
Made with Claude Opus 5.5.
The fearmongering about AI always makes us forget that NOTHING WENT FOOM, as was always predicted.
Send this to your doomer friend who has a very high P(Doom).
Accelerate.
463
851
5,616
872,223
Your PS5 Controller is now your Agent Remote.
Free & Open Source.
Works really well with the Codex app.
Also supports any agent in Ghostty.
D-pad buttons lets you cycle through agent sessions, Up button magically surfaces the exact Codex chat / Ghostty tab that needs you.
4
1
16
4,746
Full trackpad emulation on the touchpad: pointer, taps, two-finger scroll, drag, and macOS Spaces switching - everything you need works.
And of course - 27 mappable controls: 19 buttons plus eight virtual stick directions, each assignable to a Fleet action, key, or shortcut.
2
3
187
Here's the link to the repo -
github.com/AbhisekBasu1/agen…
Made with 5.6 Sol (at max reasoning effort).
cc - @Dimillian @reach_vb @thsottiaux @OpenAIDevs @tszzl
3
130
New Codex Tips >
1) Never use ultra
2) Go to model configurations and enable Max reasoning in Codex Settings
3) You can ask specifically to spawn subagents, and they all can be Max reasoning subagents now, useful for when you need them
4) Terra Max > Sol Max at writing
1
12
2,452
Bright Mirror retweeted
If you are asking “Why push back against anti-datacenter efforts?” I consider it a tragedy that anti-nuclear efforts largely strangled nuclear power in the US based on vibes, and I don’t want to see that happen to AI. Public opinion matters, and it shouldn’t be ceded unchallenged.
If you are asking “Why should I support AI efforts at all?” I believe we are in the midst of a transition more vibrant than the industrial revolution. Opinions formed a couple of years ago about the uselessness of AI are no longer valid. Millions of people and organizations are getting great returns from using it, and the demand for data centers is the market responding to the value signal. That is how progress is made!
413
1,037
7,273
887,984
We chase the feeling of awe in the external world.
While that's available for those who seek, it's also available in the act of creation.
More abundantly than most realize.
1
7
1,969
Around 20k lines of code were handwritten by me.
Rest by GPT-5.3 Codex.
Don't listen to anyone telling not to learn to code.
Learn to code.
The best time is now.
You'll be more powerful with agents and know exactly how to get the most out of them.
2
1
9
1,742
every thought can be observed. every action can be controlled. every impulse can be tamed.
the trick is to slow down to be mindful about the internal chatter. most thoughts are too fast to be questioned, but only when you're slow and deliberate-you see what's happening. also explains why typing > speaking.
1
3
1,054
Drift Inward now has memory - a new kind of AI memory where you're always in control, where you can endlessly tinker to finetune exactly what you want remembered, what needs to be forgotten.
One step closer to being the most powerful AI Journalling app on the planet 🚀
1
2
992
New essay out now, on a new X that apparently doesn't deboost links -
brightmirror.co/p/the-bitter…
1
646
Go to Settings > Accessibility, display and languages > Accessibility > Under motion, click on autoplay > Choose "Never"
You'll now be able to scroll past every video slop on the X feed, clicking play only when you intentionally want to watch something.
1
1
5
620
the model launch playbook should be clear from this picture alone.
> build the best model
> launch on @openrouter and keep it free
> win market share
> use feedback to train better models
@OpenAI tried with Quasar Alpha & Optimus Alpha, but they weren't the best
1
3
470