Who do you seek?
Erie, PA
Joined February 2026
- Tweets1.7K
- Following32
- Followers257
- Likes22.4K
I personally have been using @t3dotcodes to make this easier.
Mine is shorter: Claude builds, Codex reviews. Codex catches more of my mistakes teapaw.org/shakhzod1001/status/21…
37
I presented to an ethical hacking class this week on AI in cybersecurity.
Open-weight models are behind, but still extraordinary at producing working exploits, and due to the frontier models' safeguards, unless your approved for daybreak or glasswing access, you almost always need a open-weight model for cybersecurity.
If you're getting into cybersecurity, start playing with open-weight models and see what they can do.
Source:
anthropic.com/research/glm-5…
Local AI is the future.
Your laptop can't run a big local AI model. Your desktop can. 𝗢𝗺𝗮𝗿𝗰𝗵𝘆 4.6 lets the laptop borrow it. 🖥️
No cloud, no API bill. The model stays on your desktop at home. Your laptop just sends the questions, from the couch or the café.
How it works, 3 steps:
1. On your desktop: start a local model, then turn on Share in the Agents panel
2. On your laptop: the model shows up in the same panel. Tap Use
3. Use it in your coding agent (pi, opencode or Qwen Code), like any local model
What you'll see: the model's speed, and "2 users" when both machines are on it.
Private by default: it only works inside your own Tailscale network, and every request needs your desktop's key.
Coming in 4.6: the sharing engine is already out (omarchy-local-ai 0.6), and the panel is merged for 4.6.
Save this for 4.6 👇
Gaming PC, old workstation or DGX Spark: which box would you share from?
AI will cure a lot of diseases in the near future.
Most cells in your body carry the same DNA. But they don't use it the same way.
Google DeepMind's AlphaGenome 2 predicts how genetic changes affect specific cell types.
In one immune-cell benchmark, it identified 30% of causal variants compared with 16% for its predecessor.
Still a research tool, not a clinical test.
1
2
98
One day the big companies may be bought too...
Meta bought Conductor, the app a lot of devs run parallel coding agents in. Cloud goes read-only tomorrow, deletion starts Nov 20.
I keep saying don't marry a model. Same goes for the app around your agents. Prompts, checks and notes should live somewhere you own
31
The future is making agents dream.
This is f*cking insane. Anthropic engineer Lamis Mukta just explained why giving AI agents better memory could matter more than upgrading the model.
"The intelligence alone is not going to compound."
In this 31-minute talk, she introduces something fascinating: agents that learn from previous sessions while you sleep.
But there's a dangerous catch.
What happens when your agent remembers the WRONG solution?
A failed assumption becomes a memory. That memory influences the next run. And suddenly, the same mistake spreads across an entire AI workforce.
This is where Agent Reliability Engineering becomes critical.
Memory tells the agent what happened.
Independent verification tells it what actually worked.
And recovery loops stop repeated failures from becoming expensive habits.
The future isn't just AI that remembers everything.
It's AI that knows which memories deserve to be trusted.
Worth watching before building another autonomous agent.
Then read the complete Agent Reliability Engineering guide below ↓
1
40
Would you like to put Omarchy on an Android TV? github.com/piermark/omarchyt…
Marco Porro designed an Omarchy style launcher for Android TV. Pretty cool stuff.
1
3
232