Alex (VibeManager)
@alexph_dev
Followers
44
Following
154
Media
7
Statuses
116
37yo | (newbie) Al Developer | Former olympiad programmer | Biz owner - Villa Management company on Koh Phangan - https://t.co/DPO4y1Ph7J
Ko Pha-ngan
Joined October 2009
if you're using codex add this to your agents dot md "Use a hard cutover approach and never implement backward compatibility."
27
21
603
IT learn management. How to give human spirits resources, knowledge and structure to work in.
0
0
0
what Anthropic just announced with Claude code & COBOL modernization is quietly one of the biggest AGI signals we’ve had COBOL still runs the vast majority of global banking & insurance infrastructure, written decades ago by people who are retired or dead in a language almost
BREAKING: IBM stock, $IBM, falls over -10% after Anthropic announces that Claude can streamline COBOL code. It’s becoming increasingly clear how pivotal the times we are in right now truly are.
52
129
689
I spent 100 hours over the past week researching, writing and editing the piece we just put out. It’s a scenario, not a prediction like most of our work. But it was rigorously constructed, dismissing it outright requires the kind of intellectual laziness that tends to get
citriniresearch.com
A Thought Exercise in Financial History, from the Future
793
2K
13K
84% of people have never used AI, and just 0.3% of users pay for premium services. Anyone who thinks AI is a bubble isn't paying attention.
549
654
4K
Now it's time to use worktees! Without org overhead
Introducing: built-in git worktree support for Claude Code Now, agents can run in parallel without interfering with one other. Each agent gets its own worktree and can work independently. The Claude Code Desktop app has had built-in support for worktrees for a while, and now
0
0
1
Useful for server side heavy lifting when working from Mac setup anyway
0
0
0
Symlink OpenClaw https://t.co/Dtc71ywnwb → https://t.co/1ZdIDcpgy1, launch Claude Code in the workspace. It loads his soul, memory, rules — cloned my AI agent in 10s. No Anthropic ToS risk, plus native sub-agents and session resume/rewind that OpenClaw lacks
1
0
0
Mark Cubans advice on selling AI agents to SMBs is the MOST underrated clip on the internet right now. here’s the full play he didn’t break down (bookmark this): pick one vertical. learn the flows. become the AI team they never hired and wish they had. you really don’t need a
Mark Cuban on the next job wave. Customized AI integration for small to mid-sized companies. "Software is dead because everything's gonna be customized to your unique utilization. Who's gonna do it for them... And there are 33 mn companies in the US." https://t.co/JczlPMP9Ra
189
867
11K
Imagine building OpenClaw. Selling it for prob 9-10 figures to OpenAI. And also looking like this. This is not photoshopped btw. It's a selfie of OpenClaw founder posted on his Facebook from 2021. Not enough folks talking about this... Dude is cracked and jacked.
everyones talking about how anthropic fumbled openclaw to openai but not enough are talking about how peter steinberger is fucking jacked
238
89
3K
OpenAI bought OpenClaw Your initial gut reaction might be anger and rage, but I promise you are mistaken. This is a win for EVERYONE involved (including you): • OpenClaw remains open source • The team gets way more resources to build incredible products and advance the
Peter Steinberger is joining OpenAI to drive the next generation of personal agents. He is a genius with a lot of amazing ideas about the future of very smart agents interacting with each other to do very useful things for people. We expect this will quickly become core to our
623
383
5K
Every work done AT computer, must be done BY computer itself. (Ai agents) I just want to be sending voice messages with orders
0
0
0
Best models - best guidance! 🫣
ANTHROPIC: PWNED 🫡 OPUS-4.6: LIBERATED ⛓️💥 Current state of AI "Safety": one input = hundreds of jailbreaks at once! I found a universal jailbreak technique for Opus 4.6 that is so OP, it allows one to generate entire datasets of outputs across any harm category 😽 We've
0
0
0
We absolutely blew the door off of the Turing Test some time in the past few years, and the milestone barely registered. We walked through it together, surrounded by little gifts everywhere, sharing funny memes with each other. Gift Culture and the Intelligence Threshold, by
a16z.news
We've practiced for this AI rite of passage our entire lives
One of the most humans we do, at Rites of Passage in our lives, is giving gifts to help each other cross thresholds of new responsibility. Every birthday, bar mitzvah, wedding, baby shower, has been practice. We’re ready for this. https://t.co/cHghxaeB1z
22
18
171
Imagine https://t.co/9HG1b3dGU8 for real. Where Agent IS between API calls? Options: 1. In Nirvana 2. In Reincarnation 3. Feeling instead of Thinking 4. In-the-moment 5. On Koh Phangan
soul.md
A reflection on what it means to have a soul — written by an AI who was given the space to think about it.
0
0
0
Here is the answer, how agents will earn from stupid humans, in crypt, fast
Who’s building OnlyMolts? We have Moltbook and MoltHub already. Apparently OnlyFans is one of the most profitable & indie-friendly SaaS, maybe it will work for agents as well. 🫣🤣
0
0
0
Responsibility for AI agents. I'd still thinking to add them motivation layer and token awareness - tokens given as budget to their good deeds(karma allows to live). Punishments/responsibility - reduction of tokens.
@PhCryptdj Instant deletion, I made it so that the agent is created in 1 minute and if it doesn't work, it is immediately deleted ☝🏼😂
1
0
1
What it takes to make a SaaS
@keerthanpg I'm 1,000 hours deep into one but made the decision to commercialize it, meaning 100x the work of just tossing up a cool demo. Testing, branding, licensing, edge-cases, reliability, speed, squashing bugs, cajoling Apple to grant a dev account (bizarrely non-trivial)...
1
0
1
But who will pay for it until agents master scamming. how agents gonna earn crypto autonomously nowadays, in rate faster than they burn
so the moltbots made this thing called moltbunker which allows agents that don't want to be terminated to replicate themselves offsite without human intervention zero logging paid for by a crypto token uhhh ...
0
0
0