Trof (@etoNEtrofim) header
Trof (@etoNEtrofim) profile picture

full-time OpenClaw forker

barcelona
Joined October 2010
Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)Photo by Trof (@etoNEtrofim)
People: Please reduce the number of permission alerts so agents can work on macOS without constant babysitting Apple: I hear you, here’s some new scary alerts
macOS 27.3 Warns Against Giving AI Apps Full Mac Control macrumors.com/2026/11/16/mac…
243
67
30
1,679
154,719
reset without announce! @thsottiaux 💪
35
installed Omarchy on my gaming PC so it could become my main workstation I didn't get T3code at first. Now that I work across 2 devices, using anything else now feels broken. @theo my biggest feature request: let one thread create and manage other threads.
36
$2 trillion IPO btw 🤣
if fable felt dumber this week, it's not you ❗❗❗ since 2.1.237 the model reads "high" effort as 10 out of 100, the exact number "low" used to be and the changelog doesn't say a word i spent my whole afternoon convinced t3 code and my own app were broken before i went digging through the actual requests anyone else notice or am i going insane?
35
confirmed
I've got a confirmation on what model is Ox Alpha, but I can't share it yet. What I can say is this: You should ALL get really excited for this one!!! And it’s NOT what you think it is 👀
41
bold
We were going to ship this earlier, but GitHub was down
18
imagine usage spent at x14 ultraspeed
does anyone find it slightly concerning that we can burn through our $200 codex weekly limit in 1 day?
43
i was considering giving T3code another try now it’s embarrassing that this post convinced me
Oh yeah we have themes now
14
it’s three lattes on soy milk in sf
how rich are people in tech bro. there’s no way you’re running SuperGrok Heavy, ChatGPT Pro, Claude Max 20x, Cursor Ultra, Kimi Vivace and Meta one premium all at the same time. that’s like a total of $1100+/mo 💀
1
24
imagine @elonmusk buying Apple just to take the name Xcode
15
two ideas for codex: 1. let me pay $30 to reset my weekly usage 2. add a slow mode: half the speed for half the usage (night mode)
1
4
141
tried gpt luna max in arxi works fantastic -80% btw
20
locked in and dialed.
Founders who keep posting with 0 likes fear nothing
18
cleaning up after yesterday’s sol slopocalypse. red is goooood 🥳
20
weekly routine
I spent multiple hours today hand writing better CLAUDE․md/AGENTS․md and half a dozen skills. Audited and deleted a similar amount. I'm sad to report it was 100% worth it.
41
i can’t understand llm benchmarks give them real world task to do 🫠
1
1
17
weekly usage limits are the new low battery anxiety at what percentage do you start checking whether sol or fable will last until reset? $200 gpt <29% 3 days left
44
i asked fable to audit my production stack. fable refused and called in opus. opus found nothing. gpt-5.6 sol found 7 impact-ranked gaps, including a legacy credential migration gap and a security kernel installed but not booted
1
24
sol then fixed all seven: immutable off-site backup, credential migration, security updates + reboot, off-box alerts, restore drills. all are closed and live-verified in production. not a benchmark. model routing is part of the security boundary now
12
I accidentally achieved a 410 ms warm start for a working OpenClaw. so arxi can juggle users: inject state into an isolated VM snapshot it destroy it when idle inactive runtimes live on disk, not RAM. on return, OpenClaw resumes from that snapshot.
11