If you are using a bot in a form of Chief of staff, try exchanging the bots once in a while.
ask it about how many messages it has or usage and make it prepare a handoff for new one.
It took my 40% of my weekly limit of $200 sub in ~2 days. So I came up with that solution
ask it about how many messages it has or usage and make it prepare a handoff for new one.
It took my 40% of my weekly limit of $200 sub in ~2 days. So I came up with that solution
Short horror story @bot
0
0
0
5
👀
Nie wszystko da się pokazać na zdjęciu. Dlatego dziś zabieramy Was w krótki lot nad najwyższą obecnie budowaną estakadą w Polsce, która powstaje na #S19 Babica-Jawornik. Ciekawostka: długość najdłuższego przęsła wynosi 188 m.
Zobaczcie sami👇
#FunduszeUE #ViaCarpatia
0
0
0
51
Still getting used to how the course work, but what I really like is the BRIEF of my work on a challenge alongside my harness.
Really, it is a concept worth taking into my setup.
That kind of explanation is great! Give the big picture.
@megadevhq
Image is unrelated to brief :P
Really, it is a concept worth taking into my setup.
That kind of explanation is great! Give the big picture.
@megadevhq
Image is unrelated to brief :P
0
0
0
16
I found my MEGA pattern: The Worktree Gate.
I must say MEGA.DEV seems a different course from whatever I had to this day.
Maybe it is a future of the courses...
Congrats the team of @megadevhq and @_overment !
I feels like something new, really.
I must say MEGA.DEV seems a different course from whatever I had to this day.
Maybe it is a future of the courses...
Congrats the team of @megadevhq and @_overment !
I feels like something new, really.
1
1
4
662
I found my MEGA pattern: Model Steering. res.cloudinary.com/mega-dev/image…
1
0
1
20
Probably @megadevhq is the reason...
To be fair, I haven't shipped much since Opus 5.5 dropped. Short list of what I've done in that time:
- ts-rust, a complete rewrite of Typescript compiler in Rust that is 3x faster than the Go version
- lust-lang, an alternative toolchain for a subset of rust that compiles 100x faster
- Slopalytics, the best place to see how models compare against popular benchmarks and usage
- Slophouse (private), my personal analytics pipeline and platform for T3 Code usage
- fleethouse (private), my internal Clickhouse that gets all of my data from my cliproxy
- t3os (private for now), the start of my "perfect os for agents". Got 5 boxes running it already 😈
Got a couple small changes into T3 Code as well, such as:
- Rewrite search to be 4x more accurate
two-click repo clones to other machines (including .envs)
- "Working" sidebar section to hide working threads
- live guest thread sharing so others can watch and queue prompts 🤫
- watch_pr tool so agents sleep on CI/reviews and cut GitHub API calls by 90% while babysitting
- interactive in-app visualizations rendered straight in chat threads
- a rebuilt usage dashboard breaking down spend by cache tier, speed, and model
- one-click "Update everything" across local and remote boxes
- early compaction for idle Claude threads before prompt cache expires
t3 thread CLI to start, read, and message threads from the terminal
- PR diff badges that split line counts into code, tests, and docs
- migrating T3 Code's own typechecking onto tsc-rs
- purged over 50% of our test suite
- (and roughly 370 other merged PRs)
Pretty slow month. Hope I can pick up the pace for the rest of Q4!
0
0
0
18
I just killed my 2 biggest Grok Bots.
Every time a bot wakes up, it rereads its whole chat.
My coding lead's chat had 5,197 messages and Chief of Staff even more.
Every wake cost more than the last.
So each one wrote a handoff file.
A fresh copy took over,
with all 13 routines.
Every time a bot wakes up, it rereads its whole chat.
My coding lead's chat had 5,197 messages and Chief of Staff even more.
Every wake cost more than the last.
So each one wrote a handoff file.
A fresh copy took over,
with all 13 routines.
0
0
0
13
Can confirm the team part.
I run ~20 Grok Bots for my business in Poland.
Each has one job:
invoices, law watch, X, selling my van.
One chief of staff bot routes the work.
So I don't talk to 20 @bot .
I talk to Heniu :)
I run ~20 Grok Bots for my business in Poland.
Each has one job:
invoices, law watch, X, selling my van.
One chief of staff bot routes the work.
So I don't talk to 20 @bot .
I talk to Heniu :)
Here's my updated review of each personal agent:
1. Grok Bot
Pros: A team of bots is the easiest to understand. Free X access is amazing for research. Voice mode and the new Pages feature are great.
Cons: Email feature doesn't really work.
2. Muse
Pros: Free, best consumer atar, and business calling is amazing.
Cons: Muse Wonder is good but Opus/Astra is better.
3. Claude Duet
Pros: Most proactive out of the box. Feels polished and simple to use. Arguably the best model behind it.
Cons: Missing some features in research preview, like being able to drive its browser.
4. ChatGPT Dots
Pros: Works inside ChatGPT, so it can drive all your cloud and local threads.
Cons: Much better than at launch but still buggy. Voice mode is slow to connect.
I've also tried Instinct and some of the other agents, but I don't want more than 4 at a time connected to my email.
📌 Don't miss my full Claude Duet review here for everything that it can do: youtu.be/D-pz8L1orVI
1
0
2
62
Przemysław Stroiwąs retweeted
PHP2Shell: AI finds decade-old PHP flaws, Railway breach, Claude Duet launches morningtokens.com/issues/2026-10…
0
1
0
6
Meet my AI team, part 1: Heniu, chief of staff.
Most days I don't pick which bot does a job.
I tell Heniu.
He hands it to one of my ~25 Grok Bots.
No bot passes work down a chain.
If one hits a login, it pings Heniu, not me.
Only he may message the whole team.
Most days I don't pick which bot does a job.
I tell Heniu.
He hands it to one of my ~25 Grok Bots.
No bot passes work down a chain.
If one hits a login, it pings Heniu, not me.
Only he may message the whole team.
0
0
0
12
