Impossible to Review Every AI-Generated Code Piece
there's no way to review all code produced by ai and there's no way you're actually reviewing all the code explanations
Hybrid OpenClaw Stack Runs Locally with NVIDIA AI
I rebuilt much of my OpenClaw stack to run on local models. Getting this right is harder than it looks. I partnered with @NVIDIA_AI_PC to show you exactly how my hybrid local/hosted architecture works: https://t.co/ENr5MHcRCe
"But OpenClaw Is Expensive..."
The video tackles the soaring expense of running OpenClaw entirely in the cloud, where some users spend over $10,000 a month on hosted models. It proposes a hybrid solution that offloads the bulk of workloads to open‑source models running locally...
Improving Models Will Eventually Subsume Their Own Scaffolding
Betting against models getting better is foolish. So as we build out harnesses, memory systems, etc, how are the core models not just going to eat more of the scaffolding around them?
Prioritize First-Class Agent Memory Systems, Not Storage
Thinking about https://t.co/hdRfMQoQNm, Garry’s post made me realize we’re heading in the right direction, but we need to make agent memory systems first class in journey and make kits continuously improve. I don’t think we should store memories though, only...
Seeking Feedback: How to Improve Our Agent Experience
What can I do to make https://t.co/DZf0CS9Bqp better? Have you tried installing a kit? How was the experience? What is your agent still missing to be great?
Detect and Fix OpenClaw Documentation Drift for Success
Detecting and fixing drifts in OpenClaw docs (prompts, skills, etc) is still one of the most valuable unlocks I found. Here's how I do it: https://t.co/QPXGqbtnUS
AI Breakthroughs Become Inevitable Once Proven Possible
AI achievements are kind of like the 4 minute mile. As soon as people know it’s possible, everyone will match it.
Alex Finn Launches LLM‑Powered Personal Knowledge Wiki
.@AlexFinn just published his first kit: Personal Knowledge Wiki — LLM-Maintained Knowledge Base Seems similar to Karpathy's LLM Wiki idea. Very cool. Try it yourself here: https://t.co/CbhITuE86a
AI Breakthroughs Spark Personal Anxiety Amid Vacation
i'm on vacation with my family. i read about mythos and couldn't relax the rest of the day. i am completely stunned. i already have a severe case of ai psychosis. i dont know what to call this now. i'm...
Universal Vulnerability Disclosure Will Eliminate Software Bugs
Soon, every piece of software in the world will have their vulnerabilities exposed. And then shortly after, no software will have vulnerabilities.
Flying at 34k Ft, Still Crunching AI Workloads
Things I’m doing while flying at 34,000 feet: * Fine-tuning on my DGX Station (SSH) * Running 8 concurrent @cursor_ai cloud agents * Replying to emails * Posting on X
Fine‑tuning Gemma 4 at 34,000 Ft: Surreal Tech Adventure
Fine-tuning Gemma 4 on my DGX Station while flying 34,000 feet in the fair is a surreal feeling.
Nightly Skill Drift Detector Workflow Keeps OpenClaw Files Tidy
Keeping OpenClaw markdown files tidy was a headache. Skill files, prompts etc would constantly get bloated. It got worse when I started keeping multiple versions of each file for different models. The solution? A nightly skill drift detector workflow. Published...
Stack Shifts to Open Source with Gemma 4 Migration
it's happening... just moved LCM (lossless claw memory plugin) to use gemma 4. slowly but surely more and more of my stack is moving to open source.
