@davis7 Reminds me of an image diffusion model as well, turning static into a final copy with enough review passes/tests
English
Mike Olson
585 posts
Mike Olson
@mwolson
Engineering Manager | Staff Architect | Performance Specialist | Polyglot | Looking for Engineering Manager (Frontend / Full-stack) positions.
Berrien Springs, MI, USA Katılım Nisan 2008
114 Takip Edilen122 Takipçiler
In the process of building out my Pi extensions system I've been reading a ton more code
Swung pretty hard to not bothering reading much for a couple weeks while trying to push the limits of 5.6 (lots of really good and really bad results), but what's been interesting is how massive of a difference just a couple extra prompts makes when u know what ur doing
The functions for my file search extension (fs and rg) were "using effect v4", but also not really, it was the classic bastardized try catch hell but this time it's in an Effect.tryPromise inside a Effect.runPromiseExit in a normal fucking async function (which sucks, a lot)
I just kinda read through all of it, copied one function into pi, told it why it sucked, told it to have a subagent look into effect's node platform package, and to use generator syntax, then after like 2 more turns got actually good code
The end result is much better code than I would've hand written, but also much better code than the model would've written without direction
Fable is the closest to solving this, a lot of why it feels magical is that without having to give this extra direction it's way closer to what I actually want (but still not fully there yet, although I do think eventually it will get there)
I still think the pottery analogy is the best one rn: u start by having it make the full thing and end up with something decent, but not great. Then u slowly reshape it over and over again. The main difference is now ur reshaping with the model, which does big chunks instead of line by line
English
@theo @jullerino I've reported and have PRs open to fix a number of iOS, Android, and orchestrator v2 issues, and test what I send PRs for.
English
T3 Connect and the T3 Code mobile app are ready for a small wave of testers. Reply below with why I should invite you to test
English
Interesting way to have Fable route work to different models/providers based on cost/intelligence/taste
Theo - t3.gg@theo
This is the relevant section of my CLAUDE.md I'll be real - I haven't read it much. Just vibed out what I was looking for with Fable, and had it confirm it can use Codex for the things I care about I still find Codex to be WAY better at computer use, verification of UI/UX work, and generally more efficient at execution on well spec'd work Minmaxing this has genuinely been really fun for me and I'm loving the outputs I've been getting. I was throwing away ~50% of my end-to-end agent-driven PRs before building this workflow. I haven't had to close a single one today :)
English
@theo More expensive and not better at most benchmarks than Opus 4.8 🙃
English
Oh my god, Sonnet 5 was MORE EXPENSIVE THAN FABLE to run the whole bench 💀
Theo - t3.gg@theo
Sonnet 5 cost MORE than Opus 4.8 on the Artificial Analysis Intelligence Index
English
@Jaaneek I've been seeing issues in grok build CLI where the file_search tool will sometimes hang (on CachyOS / Arch Linux). Is this a known problem yet? Discovered while working on some (unofficial volunteer) grok stability changes for t3code in PR 3578 there.
English
@unclebobmartin @luismmolina Supergrok Heavy limits are quite good. Maxed out the $30 X Premium+ prior and only at 10% used after. Worth the $100 on promo, not so sure about $300 after promo.
English
composer 2.5 fast is pretty good, but I was running up quite a tab. Grok build is not as good. Codex is better so far. Just my impressions. Not much science.
English
Mike Olson retweetledi
I stole this idea and now use it with every single employee.
It’s the best illustration I’ve seen of teaching someone to be high agency.
It says there are 5 levels of work:
Level 1: “There is a problem.”
Level 2: “There is a problem, and I’ve found some causes.”
Level 3: “Here’s the problem, here are some possible causes, and here are some possible solutions.”
Level 4: “Here’s the problem, here’s what I think caused it, here are some possible solutions, and here’s the one I think we should pick.”
Level 5: “I identified a problem, figured out what caused it, researched how to fix it, and I fixed it. Just wanted to keep you in the loop.”
Using this framework, here’s what I say to every new employee…
You will live at Level 4 from Day 1 and as we build trust you will rise to Level 5.
Being high agency doesn’t just mean tackling problems in this way. It means your entire way of working should be oriented to being a Level 4+ employee.
Plz feel free to steal it as well.
And ty @stephsmithio for the framework!
English
Pretty neat; working further on a (probably temporary and soon-superceded) PR to improve it further here: github.com/pingdotgg/t3co…
SpaceXAI@SpaceXAI
You can now use your SuperGrok and X subscriptions inside T3code
English
aubeshim v1 is available: PATH shims for npm, pnpm, bun, and yarn that route compatible commands to aube and fall back to the real tool when needed. Per-directory globs, npx/bunx → aube dlx, mise-friendly globals.
Useful if you have 10s/100s of GB of duplicate node_modules and package manager caches.
Builds on top of aube, a fast JS/TS package manager feature-compatible with pnpm by @jdxcode, who also made mise.
mwolson.org/blog/2026-06-2…
English
Much improved, may now actually be worth trying Fable if/when it's back
Aron Prins@aronprins
Breaking News: Claude is pausing the Agent SDK credit change!
English
Took this further: claude uninstalled, comms unfollowed, totally done until they treat claude CLI and own-tools the same.
Mike Olson@mwolson
English
Same. Don't want to be penalized for T3Code usage. Forbidding bring-your-own-tools is a wild choice for Anthropic to make.
Uncle Bob Martin@unclebobmartin
I just cancelled my Claude account. I've been using codex, and haven't used Claude in several weeks.
English
For every person who replies with a screenshot of their cancelled Claude Code plan, I will donate $10 to open source.
Theo - t3.gg@theo
I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits cut by 40x, despite us doing everything right. I listened to the Claude Code team. I had my issues with their direction, but I trusted them and took them at their word. I will never make that mistake again. Until we see significant change, it is safe to assume any statement from an Anthropic employee is a lie on a timer. The rug will be pulled, no matter how many promises are made beforehand.
English
Mike Olson retweetledi
This is it.
Everything learned spending millions on longevity.
From: Your Immortal Unc and Auntie.
To: Our Immortal nieces and nephews.
0. Sleep is the world's most powerful drug.
1. Be in your bed for 8 hours
2. Same bedtime every night, any time before midnight
3. Don’t eat right before bed
4. Calm foods for dinner
5. No screens 1 hour before bed
6. Avoid added sugar (be aware it’s in everything)
7. Avoid all things in an American convenience store
8. Avoid fried foods
9. Shoes off at the door
10. Eat whole foods, particularly veggies fruits nuts legumes berries
11. Walk a little after meals or air squats
12. Get your heart rate high routinely
13. Lift heavy things
14. Stretch daily
15. Water pik, floss, brush, tongue scrape, morning and night
16. Make an effort to drink water
17. Get sunlight when you wake up (UV is low)
18. Protect skin in midday sun
19. Stand up straight
20. See at least one friend once a week
21. Avoid plastic where you can (in all things)
22. Circulate air in rooms
23. When stressed, breathe, learn to calm your body
24. Go to the dentist
25. Avoid sitting for long times
26. Protect your hearing, the world is too loud
27. Alcohol is bad for you
28. Finish coffee before noon
29. Avoid bright lights after sunset
30. If obese, look into a GLP
31. Sleep in a cold room
32. Texting while driving is dangerous
33. Turn off all notifications
34. Limit social media use
35. Don’t smoke anything
36. If you struggle to sleep, read a physical book before bed
37. 1 hour before bed have a calm wind down routine: bath, read, light walk, listen to music
38. The body is a clock and loves routine. Have a daily morning and evening schedule.
39. Avoid long distance travel where you can
40. Baby steps first: incorporate new things slowly
41. Do less… most things don’t work.
Bonus points if you get your blood checked.
Start here, it will change your life.
English
@theo Temporarily took away the frontend to give more compute to the research team maybe
English
Mike Olson retweetledi
gpt-5.5 prompt for codex seems to have a duplicated line trying to get it to not talk about creatures?
Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query.
[...]
Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query
gh link:
#L55" target="_blank" rel="nofollow noopener">github.com/openai/codex/b…
English
Mike Olson retweetledi
🚀 CachyOS April 2026 is here!
Featuring Shelly as the new GUI package manager, DNS-over-HTTPS, fingerprint sudo, installer snapshots, MangoWM + DMS, improved hardware detection, and more.
cachyos.org/blog/2604-apri…
English
@davis7 Yeah I've been noticing that opencode/qwen3.6-plus has been giving code reviews that largely agree with gpt-5.4 so I'm also looking forward to trying local qwen
English
just tried a local qwen model qwen/qwen3.6-35b-a3b on my mac (m4 max, 128gb). I'm impressed.
Had it build this page using pi for the harness. It's fast and the output is SO much better than I expected
This is the first local model I could actually see myself using. Not for my main real work, but as a secondary sub agent or random mini background thing, this is pretty sick...
English