My god they're putting grok bots bot everywhere, they're now in: - the desktop app - the mobile app - grok dot com - x dot com dms - teslas - cursor In the future I would also like my bots to be accessible from: - a really good apple watch app - my washer/dryer combo unit - my fridge - my lumix s5iix camera - a microchip in Theo's brain - my subaru crosstrek - my nintendo wii u and switch 2 (I don't want it on switch 1) - my steam deck - the youtube creator dashboard

Pros: - writing & "voice" - capabilities are on par with 6.1 sol (in non specialized things like computer use or 3d, they didn't RL on those this time) - orchestration Cons: - seriously wtf is this naming scheme you guys are making gpt-5.2-codex-high-fast seem sane - price/usage limits (tho they're working hard on fixing this) - can only use the good one (full) in muse code through the sub. no API

Went back to codex desktop today to do some tax prep stuff and holy hell the ChatGPT desktop app is falling apart There's so much here I like and want to use, but it's such a slow, janky, incoherent mess it's impossible The new "spaces" feature is actually amazing. Such a good idea that I've been building a lot of my video pipelines around, the only problem is that buggy and the UX is a dumpster fire It seriously feels like there are 5 companies all working on their own products who have to ship them all together in the chatgpt desktop app while not being allowed to talk to each other Go back and look at Dev day, they shipped 30+ features. Almost all of these are dope and useful. The problem is you haven't heard of 80% of them and it's all just floating around in this blob that's chatgpt This stuff is hard, I don't envy the position they're in. You have to keep shipping as fast as possible so you don't fall behind, but you also need time to polish and organize things. And this has to be coordinated across a bunch of teams and dozens of people and hundreds (thousands) of agents. I could go through all the specific issues but 1) it'd take too long and 2) anyone who uses it already knows most of these (very laggy, sidebar sucks, features are too hidden, spaces "tabs" system is a mess, etc.) Codex desperately needs a dictator with an actual coherent vision

Started out thinking I was gonna make a video on Dots and my issues with them, but kinda ended up just talking about "personal assistant" agents generally TL;DR: grok bot is the best one by far. Muse is good, but if ur reading this post it's not for u, and Dots needs work

I'm enjoying Astra on low reasoning + ultra fast way too much for a ton of little things like: - email management - one off fixes - research - quick demos Usage limits are still pretty brutal. Really want GPT-6.1 Sol ultra fast that's gonna be absurdly useful

Had Astra on ultrafast (on med reasoning) rebuild 1-1 from scratch on the modretro they gave us at Dev Day yesterday - Took ~3 mins - Used 4 subagents - Used ~10% of my weekly limit ($500/mo. plan) Ultrafast should rarely be used, but I'm ngl when u do use it it's really cool

Actual DeepSWE run on the ox alpha mystery model is done. Ended at ~63% NOT the 80% my first subset test got, which makes way more sense. I've been using this thing a ton and it is definitely a very good model. - Much better "voice" than Claude or GPT - Decent design - Handles subagents and long complex work quite well - Code quality is good and it does a good job of parsing what I'm asking for Have run into some weirdness: - It leaves dead code around sometimes, not nearly as "through" as something like Sol - Despite decent TPS, this thing does not feel fast at all. Especially at higher reasoning levels this thing takes forever to run, doesn't feel all that efficient. That could just be b/c I was running it in cursor, I've noticed models take longer in there and the avg tokens here seem actually pretty solid It being on around Sol medium feels about right. This thing is definitely a good model. The big question now is if the GLM-5.x flash rumors are true. If this really is a small model that could be run on something like 2x DGX sparks? It's gonna be a massive moment and a really big deal. Very excited to see this thing actually revealed.

99% sure it's GLM-5.x, all the evidence points to it (same video encoder, same tokenizer, style matches, same audio rejection, etc.) The stuff about their RL env in the GLM-5.3 announcement seemed really cool and like it could go somewhere, did not expect it to get this good this fast but here we are This thing seems absurdly good. First tests I've done have all been excellent. Already done a couple of back to back tests against GPT/Fable. It's actually doing better than they are... Seems like OpenAI and Anthropic are gonna have to start dropping models again, because this thing is (or at least seems to be) the new state of the art...

I ran this thing through 10 tasks on DeepSWE (so there could be a ton of variance in it's real score, this is a subset), but uh... gpt-5.6-sol: 52% fable: 65% whatever the hell this is: 80% (was a near miss on the "x"s so actually over 80%) I am very confused

A week later and grok bot has actually stuck in my workflow Building tons into it, feels like a next gen Hermes agent Hermes is a temperamental supercar. When it works it’s glorious, but it takes effort. Grok bot is a Tesla. It just works.

I'm currently using DeepSeek v4 Flash (running on my Sparks) to customize the DeepSeek harness. It's impressive how well it's doing, feels to be about at the level of GPT-5.4 or Opus 4.5. But comparing it to using GPT-5.6 Sol to customize Pi it's not even close...

This is from a recent YouTube video by @davis7 and I absolutely agree with his characterization here though I think it under-sells 5.6 Sol a bit. The benchmarks don't accurately convey everything.

Effect v4 Release Candidate is here! After months of beta releases, real-world usage, and community feedback, v4 is entering the final stretch before stable. Try it, migrate, test your integrations, and tell us what still breaks before 4.0. ↓↓↓

full triage and fixes submitted for all open issues on btca done in a proper graphite stack just told it to do this, came back 10 mins later and it's done. feels like the ultimate async model...