@AgiMaulanaXyz Turned out I was flagged by #github for suspected abuse. Not really sure why. Filed a reinstatement request. The support is taking their time for the 2nd day.
@Alibaba_Qwen Seems like the approach used needs to be inserted into my review prompts even before I lay my hands on this model:
- Analyse input
- Analyse startin environment
- Try to simulate hiw the environment will change
- Assess blast radius
- Report
My son asked me how I can trust #LLMs when they do make so many mistakes.
— Son, — I said, — you just make the agent #loop in a parallel 3-aspect #subagent review-and-fix cycle until there is nothing to fix.
— Thanks pa, — he said. — Crystal clear now.
Working with #aiagents changed the way I #think now.
Used to deep dive into one task and forget about anything else.
Now I have a few agents working at the same time and switch between them constantly.
Skills needed:
Before: deep concentration
After: load/unload context fast
One of the most interesting experiences was using @opencrabs to develop @opencrabs.
Remember that scene from Master and Commander where the surgeon - played by @paulbettanyhq - extracts a bullet from his own guts?
Something like that. :)
v0.3.42–v0.3.45 JUST DROPPED 🦀🔥
🤝 Xiaomi MiMo collab: 6 days left of free and unlimited AI, no API key needed.
🧠 AI catches itself looping and force-cancels
📁 Files archived on session delete, not lost
🔒 Cron jobs protect themselves
🔍 Web search DDG Lite
🎯 Plan pinning for focused execution
🖥️ Mission Control shows prompts, delivery, history
⚡ Evolve stability: migration guard + race fix
👥 Cowork workspace with QR + deep link
🔧 Config auto-repairs broken toml
📱 Sessions auto-rename across channels
60 COMMITS • 4,019 tests • 4 releases
Get it 🧵👇
I fired my assistant bc of @opencrabs.
Today it:
- scanned my telegram for notifications about new leads for our latest #RealEstateInvestment offer
- scanned again to see my chats with those leads
- agreed with me follow up / close decisions
- sent follow ups
5 mins. Boom.
@pydantic@opencrabs We decided not to use any frameworks at all.
Not sure if in the age when code is so cheap it is worth it to learn other frameworks (especially for easier tasks) instead of just building our own.
Faster, more control, less risks.
Used @opencrabs to build evals for @opencrabs.
@pydantic@opencrabs We decided not to use any frameworks at all.
Not sure if in the age when code is so cheap it is worth it to learn other frameworks (especially for easier tasks) instead of just building our own.
Faster, more control, less risks.
Used @opencrabs to build evals for @opencrabs.
Best eval framework for an agent harness and why?
@pydantic evals? #aws agent-evaluation? agenta? giskard? What else?
Looking to build an eval suite for @opencrabs
Looking for people selling @openclaw agents!
How do you charge your clients?
A baloon payment? Monthly fee?
Do you include LLM tokens and hosting into your bill or let the client have their own LLM account and host on their own?
Do you charge for onboarding new users?