Object Orienter (@Neotk) profile picture

Rocket ship builder, pizza expert, loves the Giants, parent.

Joined March 2009
Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)Photo by Object Orienter (@Neotk)
I've been running OpenClaw as my always-on personal AI assistant for months — Telegram, Discord, WhatsApp, iMessage, Gmail monitoring, calendar, proactive alerts, the works. Claude Code Channels + Cowork + Computer Use have closed the gap dramatically in just one week. But here's what's still missing for a full replacement: 1. Daemon mode — OpenClaw runs as a headless LaunchAgent 24/7. Claude Desktop needs a GUI session open. Ship a claude-daemon and it's game over. 2. Always-listening channels — OpenClaw receives messages and responds proactively. Claude Channels require an active session with --channels flag. No event-driven "inbox". 3. WhatsApp/Signal — Channels only cover Telegram + Discord. Many of us live on WhatsApp. 4. Group chat participation — Channels are DM-only. Can't monitor and participate in Discord servers or Telegram groups. 5. Multi-provider routing — Sometimes you want GPT for a quick task or Gemini for a specific workload. OpenClaw routes across providers. The trajectory is clear though. @trq212 and team shipped Dispatch, Channels, and Computer Use in ONE WEEK. At this pace, most of these gaps close within months. The moment Claude ships a headless background service, the migration becomes real.
1
1
6
810
I couldn't find a way to pilot this to be honestly. Would you have any particular guidance?
1
775
Why are people so obsessed with being anti-ai despite not really being able to recognise what is AI and what is not?
26
Did Apple seriously released an iPad mini with OLED WITHOUT PRO-MOTION? Are you kidding me?
54
Voltaremos.
5,847
8,007
1,560
83,837
2,735,535
Faz o Sua Melhor Versão. Já faz um Jiu Jitsu com o @CascaGrossaReal
1
44
Replying to @Allonsyyy_
Specially from commentators. They are the ones that should be endorsing the players.
77
Replying to @Allonsyyy_
Hey Allonsyyy I’ve been working hard on making the best gundam simulator. The community is growing in there. Why not give it a try? Newtypearena.com. Happy to show you a demo on a discord call :) By the way, love your videos :)
2
Very accurate
My current model rankings S - Opus 5.5, Muse Wonder A - GPT-6.1 Sol — Gap — Everything else
1
27
Object Orienter retweeted
Dos 14 candidatos, apenas dois são explicitamente bandidos. Mesmo assim, 92% dos eleitores escolheram o crime. A gente merece o Brasil que tem.
516
3,378
188
19,924
297,148
Replying to @thsottiaux
@thsottiaux I need a new reset :P
18
Object Orienter retweeted
I use effort low a lot more when I want to stay in the loop, and effort max is basically only if I want zero input or want to find security vulnerabilities.
27
40
11
581
58,289
Replying to @theo
Miss not having 5hr limit.
3
2,488
Object Orienter retweeted
Que perigo
88
317
17
5,002
108,812
Replying to @theo
So true! I never know how much thinking what I'm asking requires. It's such a dumb option to expose to the user.
1
487
Replying to @jessethanley
I just wish they don't have the annoying 5 hour limit. My Opus decided to spin up some agents being 2 of them Fable agents, my 5 hour limit went dead.
31
Replying to @buildwithrajath
Yes... because my Opus work keeps hitting the very annoying 5hr limit.
319
The biggest win from ChatGPT over Claude during these last 2 weeks I've been using ChatGPT is not having the very annoying 5 hour limit. I wish Claude had that.
19
Replying to @theo
@theo It would be really cool if T3 could let you continue the work with a different LLM if you hit your limit with the one working at the moment.
9
Replying to @thsottiaux
OMG SO ON TIME!!! Tibo you legend!
15
12
106,291
Yep, for the first time in over a year I’ve cancelled my Claude subscription. Astra is really good.
GPT 6 Astra is so much better than Fable 5.1. Fable 5.1 is slow, expensive, and lazy. I spent the past 12 months using Claude Code as my daily driver. I use Codex now. Astra is fast, reliable, and computer use is a genuine game changer. It does things no other model can do. GPT 6 Astra has completely taken over my workflow.
205