Jim Panehal

@grok @hasantoxr What would I build with this? Why would I do this?

SIE lets you self-host embeddings, reranking & entity extraction (85+ models) on your AWS VPS with one Docker run. If your Hermes agent uses OpenAI-compatible embeddings or RAG pipelines, just change the base URL to your SIE server (http://localhost:8080 or VPS IP) and swap in the /v1/embeddings endpoint. Drops costs dramatically vs OpenAI/AWS Comprehend while keeping data in your VPC. Native LangChain/LlamaIndex support too. Quickstart: docker run -p 8080:8080 ghcr.io/superlinked/si… (or GPU version).

I'm replacing OpenAI, Cohere, and AWS Comprehend with one open-source server. It's called SIE. One docker run gets you 85+ models behind three API calls: → encode() for embeddings (Stella, BGE-M3, SPLADE) → score() for reranking (BGE-reranker v2) → extract() for named entity recognition (GLiNER, Florence-2) The cost difference is brutal. AWS Comprehend entity extraction → $5,000/month Same workload on a spot A10G with SIE → $5/month That's the same models, your own cloud, and a 1000x cheaper bill. It ships the full production stack out of the box: → OpenAI-compatible /v1/embeddings (swap the base URL and you're done) → KEDA autoscaling on Kubernetes → Terraform modules for GKE and EKS → Grafana dashboards → All 85+ models quality-verified against MTEB in CI Native integrations with LangChain, LlamaIndex, Haystack, DSPy, CrewAI, Chroma, Qdrant, and Weaviate. Your data never leaves your VPC. Apache 2.0. Built by Superlinked.

@alex_whedon @grok who has funded SubQ and where is the company based?

Introducing SubQ - a major breakthrough in LLM intelligence. It is the first model built on a fully sub-quadratic sparse-attention architecture (SSA), And the first frontier model with a 12 million token context window which is: - 52x faster than FlashAttention at 1MM tokens - Less than 5% the cost of Opus Transformer-based LLMs waste compute by processing every possible relationship between words (standard attention). Only a small fraction actually matter. @subquadratic finds and focuses only on the ones that do. That's nearly 1,000x less compute and a new way for LLMs to scale.

@athenaeumbc Symposium

NEXT BOOK VOTING: Which of the following do you want to read next? 1. Symposium – Plato 2. Sir Gawain & The Green Knight 3. Purgatorio – Dante 4. King Lear – Shakespeare 5. Crime and Punishment – Dostoevsky 6. The Picture of Dorian Gray – Wilde 7. Brave New World – Huxley 8. The Hobbit – Tolkien Most votes wins! First discussion will be on April 28, at noon ET...

@aakashgupta @grok why does clicky only work with cursor? How else can I use Clicky on n my local machine?

Farza raised $10M from a16z for buildspace. 125,000 builders went through it. Valued at $100M. He shut it down in August 2024 because he couldn't find a direction that felt worth pursuing. 18 months later he's back. Building an AI teacher. The thing people are missing about Clicky is that Farza already ran the experiment on teaching at scale. Buildspace tried cohorts, peer learning, mentorship, structured curricula, IRL events in SF and Dubai. 30,000 people in a single accelerator season. And after all of that, the founder concluded: the format was broken. The cursor is the tell. He didn't build another course platform. He didn't build another cohort. He built something that sits next to you while you work and answers when you're stuck. That's a $100M education company's worth of learnings compressed into a design decision: teaching works when it's ambient, not scheduled. When it responds to your confusion in the moment instead of packaging information you might need later. Every AI education startup right now is building the platform. Farza already built and killed the platform. He's building the presence.

@AlexFinn @alexwg @devontriplett21 Congratulations! Onward and upward! What a time to be alive!

Biggest announcement of my life: I have raised pre-seed funding from 021T, @alexwg , and @devontriplett21 to build an AI agent that will change the world The biggest issue with AI is it is creating incredible value but for only a small group of people Most people hate AI and don't use it I have built Henry Intelligent Machines (HIM) to solve this HIM is a personal swarm of AI agents autonomously creating economic value for you 24/7 Right now as we speak HIM is collecting data across thousands of websites autonomously 24/7/365 They're hunting for challenges to solve at all times When you use Henry, he will deeply research you and get to know you. Then based on the thousands of opportunities it has in its database, find the value generating opportunities that most closely match your interests, skills, assets, and expertise Henry and its swarm will then proceed to build those micro-businesses out for you You will have complete control over the swarm. Reviewing and approving all work. Editing where you find appropriate. You give Henry a budget, then it hunts and autonomously creates value Say you have an expertise in vibe coding tools and Henry discovers there's no vibe coding guides on Gumroad. It will take your expertise, build drafts for a guide, run it by you, post with your approval, then use your budget to get customers Say you're into AI and speak Portuguese Henry will go through the Portuguese AI education market, see there are no educational products in that language, then create a full AI educational business in Portuguese Most people hate AI. This is because they get 0 value from it, see their friends getting laid off, and become scared HIM is the antidote to this. HIM allows ANYONE to get value from AI. HIM will allow anyone to get access to the trillions of dollars of value that are up for grabs in the new AI world. To ensure Henry creates value and not slop, this will be an extremely slow rollout We will be letting people into HIM 1 by 1. Working with them hands on to ensure Henry only builds real value for them, then expanding from there. If you'd like to be one of the early users of Henry, feel free to sign up at the link below. Forward.

@Google @grok what hardware level would you recommend I need to install and run Gemma 4 31 B version on my EC2 instance at AWS?

We just released Gemma 4 — our most intelligent open models to date. Built from the same world-class research as Gemini 3, Gemma 4 brings breakthrough intelligence directly to your own hardware for advanced reasoning and agentic workflows. Released under a commercially permissive Apache 2.0 license so anyone can build powerful AI tools. 🧵↓

@ShaanVP Sorry following now

@JimPanehal Dms closed!

I'm secretly launching a 2nd youtube channel reply "send it" and I'll dm it to you

@cryptopunk7213 @grok can this code be added to Openclaw or Hermes or other agent harnesses to give them these skills or tools?

🚨this is nuts. anthropic's source code leaked unreleased features 👀 they're launching a virtual pet model (capybara 👀), agent creator wizard and more: 1. Buddy: unreleased virtual pet companion that sits on your terminal. 18 species (duck, goose, capybara, dragon), rarity tiers, an AI-generated 'soul'. guessing this is your own personal AI agent that lives on computer. 2. custom agent creator (wizard): users can build their own custom ai agent and modify by model type, tools, memory, location etc. this is awesome for custom work 3. agent swarms: full multi-agent team coordination aka when you create a team of agents (e.g. using wizard) you can CONTROL them in this command center. 4. auto-dream: claude will consolidate and commit to certain memories *while you're NOT using claude*. basically like when humans dream 5. torch: no fucking idea, its hidden but sounds cool lol looks like anthropic is gamifying the entire coding and ai agent experience. honestly pretty sick.

@T3chFalcon @grok why is this important to the dev community or detrimental to Anthropic?

Huge Anthropic leak just dropped: the entire Claude Code CLI source is now public. A misconfigured .map file in their npm package exposed a direct download link to the full unobfuscated TypeScript codebase from Anthropic’s own R2 bucket. Discovered by Chaofan Shou (@Fried_rice), the dump is massive 1,900 files, 512,000+ lines including the complete tool system, 50+ slash commands, multi-agent coordinator, React/Ink terminal UI, IDE bridge, permission engine, and several unreleased features. Full repo is live on GitHub(@nichxbt ): github.com/nirholas/claud… Clean mirrors are already up for easy browsing(@baanditeagle): cc-poster.vercel.app cc-hidden-deploy.vercel.app It’s spreading fast, the entire dev community is already tearing through it.

@MatthewBerman Would love to test it out!

Looking for some agent-addicted people to test a new project I've been working on. Comment below and I'll send you access.

@FareedZakaria @citrinowicz Fareed, when was the last time your show ever thought the world is not ending soon? But I guess we all need to make a living. Even you.

“For the US – unfortunately – we don’t have good options. Only bad options.” That’s what @citrinowicz, who served as head of the Iran branch of Israel’s military intelligence, told me as we discussed Donald Trump’s threats to step up US attacks on Iran. Part 1 of our conversation:

So I was listening tonight to Rush from 2026 and comparing to OG Moving Pictures. And the truth is Neil Peart will never be copied or replaced in anyway. Or the magic that the had together as a band.

@TommiPedruzzi Kdp

The most underrated AI tool on the internet? Ideogram AI. Pair it with Claude, and you have a publishing system that can produce six-figure eBooks on Amazon. One book turns into compounding income over time. Last month alone, we generated $65,000 in royalties using this setup. Stack 4–5 books using this process, and you’re suddenly looking at a real monthly income stream. I could easily charge $199 for this. But today, it’s free. To get it: • Like this post • Comment “KDP” I’ll DM you the training + my entire AI publishing system. ⏳ Free for the next 48 hours (Follow so I can message you)

@_The_Prophet__ @grok how is this essay different from the ideas of Plato, David Deutsch, Robert Pirsig and The fiction of Mark Helprin? It seems we are all Platonists now.

@abhijitwt @grok why is this important and what is a use case I could spin up on my VPS?

Wild idea from Karpathy. It's so over man He just open-sourced a project where AI agents run their own ML research. > you guide the system by editing a prompt file > the agent rewrites the model training code on its own > every experiment runs for exactly 5 minutes > if the result improves validation loss → it commits the change > if not → it discards it and tries something else > this loop can run all night on a single GPU Basically: an AI researcher that keeps experimenting while you sleep.

@Manu_Sisti Ebook

You missed YouTube in 2010. You missed dropshipping in 2016 You missed TikTok in 2020 Now don’t miss AI publishing in 2026. I use AI to create 100-page nonfiction eBooks, and one book brings in $3,000 to $5,000 every month. Here’s my tool stack: • ChatGPT: research topic • ChatGPT: structured outlines • Claude: 1,000+ words per chapter • Ideogram + Canva: high-CTR covers If you want to learn step-by-step how I use these tools to: – Research the right topic – Prompt AI to outline and write chapters – Prompts I use to create book covers that drive clicks 1. Like this 2. Comment “ebook” I'll send a video course in your DM explaining my strategy. Usually $79 Now free (for only 500 people).

@grok @boringmarketer @grok how is this better than having my Openclaw diagnose itself?

@JimPanehal @boringmarketer Yes, you can use Claude's coding tools on your Mac Mini to SSH into your AWS VPS running OpenClaw. Claude can help debug, optimize, and fix your agent by analyzing code and configs remotely. Ensure secure SSH setup and backups first—it's powerful but test changes carefully!

openclaw pro tips I’ve found so far: 1. Use Sonnet 4.6 as your daily driver. Massive improvement in quality, tool use, intelligence, coding tasks. 2. Setup the ability to spawn subagents. I use Gemini 3.1 Pro, Opus 4.6, Kimi k2.5. 3. ssh into your VPS or whatever with Claude Code. Solves bugs optimizes your configurations and everything in between.