ethan
7.7K posts


Idk man qwen 3.5 ordered my groceries for me. Maybe you just have skill_issue.md
Peter Steinberger 🦞@steipete
@sbaratelli @nvidia @openclaw most folks will want as much intelligence as possible, and open models aren't there yet.
English

hey your 128K model might be using a fraction of its context and you don't know it.
llama-server splits your context window across parallel slots. if you set -np 4 on a 128K context you get 32K per slot. on 32K context with 4 slots you get 8K each.
that's why long conversations get cut off. not the model. not the quant. just slot splitting eating your context.
fix: add -np 1 to your launch command. one slot. full context to one user.
if you're running locally for yourself you don't need multiple slots. you need one slot with the full window.
English

Clanker cloud roblox tycoon
kache@yacineMTB
prediction: someone is going to get a coding AI like codex to automate turning existing steam video games into harnesses, come up with architecture to parallelize the games themselves in a manner that is conducive for RL training, and train an RL demigod model
Nederlands

@0xKofi There are not hours in the day to review all the code I am generating.
Just like I wasn't reviewing the code my reports were generating when I was a manager.
English

I've been seeing a lot of folk on the timeline say IDEs are dying. But I don't get it. Are you guys not reviewing the code your agents generate 😅
Alex Kaplan@alexkaplan0
I hear the same. The IDE is dying. Everyone's managing agents now--mostly local, some cloud. Honestly Devin from @cognition is extremely slept on as the SOTA SWE agent.
English
ethan retweetet

🚨‼️ CRITICAL: Ubiquiti UniFi Network Application vulnerabilities were just disclosed
CVE-2026-22557 CVSS 10.0
Remote path traversal vulnerability allowing an attacker to access and manipulate files, leading to account takeover. No authentication required.
CVE-2026-22558 — CVSS 7.7
Authenticated NoSQL Injection allowing privilege escalation.


English







