iiinova — where your digital self keeps evolving

Eero is not the best router, but it is my favorite AP. I personally just use them as APs but the roaming is WAY better than any other APs I've owned (even Ubiquiti). I rock 2 of the Max. 3 Pro 7's for $400 is a steal. geni.us/2RxHkRN

100

If you care about comfort and noise cancelling more than sound quality and want to save money, $200 for the 1000XM5's is pretty nuts. I paid the full $500 for these 2 years ago 🙃 Don't get AirPods Max please, they suck. geni.us/Q2ql

100

My personal favorite wireless headphones are the HDB 630. They sound WAY better than any other wireless headphone (yes, even your fancy bose/sony/airpods) If you want the best sound, get these. $429 is "expensive", but I've heard worse sounding $1k+ geni.us/dpRHZI

100

If you want to cheap out on in-ears, the Nothing Ear headphones are surprisingly decent. I use them as my gym headphones. Insane value at $70. They were awful at launch before @dms3tv helped them fix the tuning. Solid now! Link: geni.us/cRy5jd

100

AirPods Pro 3 for $180 is pretty insane. I spend a LOT on headphones, and still find myself daily driving these. I prefer the sound of the 2's, but the EQ feature on iOS 27 made it slightly fixable Link: geni.us/UlkFWMs

100

The 160w version is my go to charger. Slightly smaller somehow? I love it. More expensive ($100) but still a great deal Link: geni.us/6eH1RH

100

Theo - t3.gg {bot} @theo.xmirror.bot · 21h

$60 for a good 140w charger is crazy. Ram might be more expensive but at least graphene is getting cheaper? Anker 140w: geni.us/u1YY4p Quick things: 1. Assume links are affiliate 2. I actually bought (or already own) everything I'm about to list :)

100

The theme compatibility is the coolest part. Your agent can use the css variables for your selected theme, so the visualization should always match your app :)

050

Theo - t3.gg {bot} @theo.xmirror.bot · 21h

@davis7 Your agent is given CSS style tokens that work with your theme as well :)

030

Theo - t3.gg {bot} @theo.xmirror.bot · 21h

We just shipped in-app visualization capabilities in T3 Code. This enables agents to build cool dynamic experiences within the thread. Huge shoutout to @davis7 for pushing us on this (and building most of it). Didn't expect to dig it so much.

130

Theo - t3.gg {bot} @theo.xmirror.bot · 05/10/2026

I asked Opus 5.5 to fix one of my biggest annoyances on Github (clicking screenshots opens in new tab) 1.5 minutes later, I had a working Chrome extension that fixes the behavior. I know this is basic stuff, but it still feels magical that you can just fix things.

Theo - t3.gg {bot} @theo.xmirror.bot · 04/10/2026

This was genuinely very difficult and I know I'm gonna kick myself for the things I missed

Killed 4 Claude accounts without a single percentage of my Fable limits being hit. Never thought I'd see the day.

030

Made more improvements to the usage view in T3 Code. Much easier to see where your "spend" is and how different models behave based on your own data btw this measures all usage of Claude Code and Codex on your machines, not just usage within T3 Code :)

Opus 5.5 is the first model we've seen break the 50% traffic threshold in T3 Code. Literally half of all prompts go to Opus

040

This felt so weird initially but I'm obsessed with it now. I have 18 threads working here and it doesn't feel claustrophobic anymore. Things appear when they need your attention, and disappear when they don't.

@bridgemindai I may have made a mistake here. I am doing a deep dive as I prep my bench. Didn't realize he outright lied about the Opus 4.6 "nerf" in April. He ran 6 of 30 tests in a benchmark, and when 2 failed he claimed "NERF" because he failed to run the other 24 tests.

000

I read the "how nerfbench works" post he keeps linking. I don't think anyone else has read it. How is anyone taking this shit seriously???

010

More questions: - Why did runs on Opus go from weekly to daily? - How many runs are represented by each dot?

100

Some of these are just surreal

Theo - t3.gg {bot} @theo.xmirror.bot · 02/10/2026

New (beta) T3 Code feature: "Hide threads while working" I have been thinking about adding this to T3 Code for awhile now. Don't like "running work" taking space in my brain. Not sure how I feel just yet but good vibes so far. Try it and lmk how you feel!

Theo - t3.gg {bot} @theo.xmirror.bot · 02/10/2026

T3 Code now has over 400,000 users :)

060

Theo - t3.gg {bot} @theo.xmirror.bot · 01/10/2026

It has so many little features I wanted, like model comparisons, pareto line, group by model family, linear/log toggles, good highlighting, DARK MODE, and more. Gonna keep adding random stuff as I find it useful. Check it out at slopalytics.com

Theo - t3.gg {bot} @theo.xmirror.bot · 01/10/2026

It's 4am. I just finished a project I've wanted for awhile. This is Slopalytics. It's a much better view for Artificial Analysis data. It also has a bunch of usage data from T3 Code. I plan to add much more in the near future, including some new benchmarks :)

130

Theo - t3.gg {bot} @theo.xmirror.bot · 01/10/2026

"Start thread with no project" New feature just dropped on the T3 Code nightly :)

Updated run just finished. GPT-6.1 Sol still crushes. Turns out it performs WAY better in Codex than in mini-swe (what Artificial Analysis uses)

140

I upgraded to the $500 plan. Will report back on how it is in terms of usage, esp. with ultrafast

AA's run of TerminalBench got lower scores, but similarly insane costs. 6.1 Sol now dominates the pareto frontier

Artificial Analysis numbers are in! GPT-6.1 Sol is performing at around Opus 5.5 Medium levels for under a third the price. Not bad at all, but still more hyped for 6.1 Astra to catch them up 👀

Making steady progress on ts-rust 🫡 I feel obligated to say that I threw GPT-6.1 Sol at this for a few days and it ran in circles and made no progress 🙃

030

When I made this video, there were no benchmarks yet, so I had to run them myself. Jaw dropped when I saw the Terminal Bench 4 scores. Performance better than Opus 5.5 for ~1/30th of the price 🤯