@Dexerto Yeah, well sucks to suck because my iPhone 14 I dropped 1 million times before the screen ever had any damage my newest iPhone 17 two drops and I got cracks at the bottom
OpenAI's keyboard: $230, RGB lights so you can watch your agent think.
Mine: a hacksaw, some Christmas lights, $0 unit cost.
No approve key on mine though.. be honest, you were hitting it anyway.
#OpenAI#Codex#AI#Agents
You know, I see both sides to this, and normally I would agree, and I hate to have exceptions. Memory in context is just so important, and I myself literally was just about to dump my memory pursuits and just fully surrender to super memory because I've always loved it. Seeing this tweet, even though it probably won't affect my decision overall long term, at least lets me know to monitor the situation and make the change at an appropriate time. While I would normally agree, it might have saved me a headache at least while it gets figured out.
Six patents. One thesis.
LLMs got smarter. They didn't get wiser.
CT | KEOS | STG-EUT | MKP
Memibrium | Sovereign Edge AI
Each closes a gap between what models do and what regulated industries can deploy.
Papers and filings below.
Field-of-use licenses open.
13 months ago I couldn't build a login screen. Funny how that works.
OpenClaw doesn't belong in production.
We built PokeeClaw — enterprise-secure AI agents, zero setup, 1,000+ app integrations.
Try now: https://t.co/uX6VsZ6p0c
First 500 to follow @Pokee_AI, comment “PokeeClaw”, like & repost get 1 month free.
@supermemory I get wanting it to be a developer API key versus a personal API key for the Claude Code Super Memory plugin, but not giving me a way to transfer my memories from personal to developer in order to do that is just cruel and unusual punishment 😂😅
I've been building a personal brand around the idea of "Synthesizer" pattern-matching across industries, triangulating insights from multiple sources.
Today I learned Palantir's core AI architecture is literally called the "Synthesizer K-LLM."
Same thesis: Why trust 1 source when you can triangulate across K?
Sometimes you're not ahead of the curve.
You're just standing in the same place the curve is heading.
Markdown Linting: Simple Hack + Huge ROI
When you’re new to AI-driven workflows, proper documentation is your lifeline. But here’s a less obvious insight:
Formatting your Markdown matters—a LOT.
I learned the hard way that using emphasis (like wrapping titles in *stars*) confuses AI tools like ChatGPT or Claude. They treat emphasized titles as plain text, leading to walls of indistinguishable text.
Instead, clearly structure your docs using proper Markdown headers (#, ##, ###).
Quick tip:
Grab a Markdown linting solution ASAP (e.g., markdownlint).
Run it on all your docs to quickly spot and fix these formatting issues.
The ROI? Huge.
AI instantly grasps your document structure.
Responses become sharper and context-aware.
Your workflow becomes smoother and more efficient.
Tiny tweak, massive gains. Give it a shot.
#Markdown #Development #Codingtips
POV: Everyone’s losing their minds over Claude Code subagents today and you’re just sitting there like 🧍♂️
Me for the past 3 weeks:
“Hey Claude, split this into 4 parallel tasks”
Claude Code: “Sure thing”
spawns 4 subagents
Me: “Cool”
Everyone today: “OMG SUBAGENTS ARE REVOLUTIONARY! GAME CHANGER! PARALLEL AI AGENTS!”
Me: “…wait, was that not supposed to work?”
Apparently I’ve been accidentally using “cutting-edge multi-agent orchestration” when I thought I was just asking nicely for help with my refactoring.
Next you’re gonna tell me that saying “think harder” to get better results is some kind of advanced prompt engineering technique and not just me being demanding. 😭
Currently wondering what other “undocumented features” I’ve been stumbling into by just talking to Claude Code like a normal human being
#ClaudeCode #AccidentallyAdvanced #TwilightZoneMoment #UltraThink