Michael Dotaona

God first Matt 6:33🕊️🇵🇬Occupy until Jesus Christ returns✝️Don't abandon your stewardship for your citizenship✝️

[Future Logic @the_futureAI]

Google laid him off. So he pointed Google’s own AI at Bitcoin—and reportedly made over $400K.

The wild part? TimesFM was **never trained on Bitcoin**. It was trained on 100B+ time points from things like search trends, Wikipedia traffic, and demand data.

Instead of retraining the model, he simply prompts it with the latest BTC data every 5 minutes.

The bot then:
• Predicts the next candle’s probability range
• Compares model odds vs. market odds
• Trades only when there’s a meaningful edge
• Uses strict filters, Fractional Kelly sizing, and daily loss limits

No emotions. No guessing. Just data-driven trading.

I’m giving away the complete setup and breakdown for free.

Like, repost, and comment “GOOGLE” — I’ll DM it to you.

[Michael Dotaona @borderlogix_md]

@the_futureAI Google

[Michael Dotaona @borderlogix_md]

@aftahi_ai fable

[Rituraj @RituWithAI]

🚨 Hugging Face just open sourced a complete real-time voice AI pipeline.

Speak. It listens. It thinks. It talks back. End to end. Running on your GPU. Free.

No OpenAI Realtime API fees. No ElevenLabs per-character billing. No Google Cloud per-minute pricing. Just a GPU and an internet connection.

It's called speech-to-speech. Built and maintained by Hugging Face. And it does something no other open-source project has assembled cleanly until now.

Here's what makes real-time voice AI hard.

Every voice AI pipeline has four stages: speech recognition (you speak → text), language model (text → response text), text-to-speech (response text → audio), and audio output. Each stage adds latency. Chain them together naively and you get a system that feels slow — the pause between you finishing a sentence and the AI starting to respond breaks the conversational illusion.

speech-to-speech is built around minimizing that latency at every stage simultaneously.

Here's the full stack it ships with:

Speech Recognition (STR):
→ Whisper (local) — OpenAI's transcription model, runs fully offline
→ Faster-Whisper — 4x faster inference with same accuracy
→ Distil-Whisper — smallest and fastest, lowest latency
→ Paraformer — Chinese language specialist
Language Model (LLM):
→ Any Transformers-compatible model — Llama, Mistral, Qwen, anything
→ Any OpenAI-compatible API endpoint — swap in Claude, GPT, Gemini
→ MLX-optimized models for Apple Silicon — runs efficiently on Mac
Text-to-Speech (TTS):
→ Parler-TTS — controllable voice with description-based prompting
→ MeloTTS — multilingual, fast
→ ChatTTS — natural conversational prosody
→ HF Inference Endpoints — offload TTS to Hugging Face servers when needed
Mix and match. Any STR with any LLM with any TTS. Test combinations. Find the lowest latency stack for your hardware.
Here's the wildest part.

It ships with a Language Model Speech (LMS) mode — an experimental architecture where the LLM generates audio tokens directly instead of text tokens. No separate TTS stage. The model thinks in audio.

This is the architecture that makes GPT-4o Advanced Voice feel natural — the model is generating speech as a native output, not converting text to speech after the fact. HF's open-source version lets you experiment with this architecture on your own hardware.

And there's a VAD (Voice Activity Detection) system that detects when you stop speaking in real time — no fixed silence threshold, no manual push-to-talk. The pipeline responds the moment you finish a sentence.

Here's the cost comparison that makes this worth caring about.

OpenAI Realtime API: $0.06 per minute input, $0.24 per minute output. A one-hour conversation: $18. A developer building a voice AI application with 1,000 daily users: $18,000/day in API costs.
speech-to-speech on a single A100: $0. Your only cost is the GPU rental.
For production voice AI at any scale, the economics are not close.

One command to install.

9.6K GitHub stars. 944 forks. Apache 2.0 License.

100% Open Source. From Hugging Face.

GitHub link in the comments 👇

[Ruben Hassid @rubenhassid]

Stop buying expensive $500 courses to learn AI.

I’ve already done it for you. With one list:

Straight to the point. Zero confusion. And no fluff.

Spend a day mastering Claude here: https://t.co/Vn60ElPZ2i

Claude 101: https://t.co/HNa5MrCLVU
Claude Fable-5: https://t.co/682TA10gmu
Claude Cowork: https://t.co/AvO8fCLTrL
Claude Code: https://t.co/O2kJvFkgan
Claude Skills: https://t.co/jT4uB5Bdjw
Claude Design: https://t.co/q1zjMfeAyg
Claude for Excel: https://t.co/7g3CFNcKrs
How to Prompt: https://t.co/EE46WHU8vg
Claude + Linkedin: https://t.co/9d5stC6grm
Be good at Claude: https://t.co/SVGd967eMQ
Stop writing like AI: https://t.co/JWKUGNKgOS
Claude for your team: https://t.co/U1JsBVCzYH
Claude Connectors: https://t.co/TSAQqOpDeV
Set up Claude Cowork: https://t.co/diDhiKkfjs
Stop Prompting Claude: https://t.co/j1LATSJiat
Claude to sound like you: https://t.co/kDGBpSF7Wh
Stop hitting Claude limits: https://t.co/j5fEzSH5br
Stop using Claude at work: https://t.co/c6X55Thy6t

1. Save this list for later (three dots, top right).
2. Share it with a friend by ♻️ reposting this image.
3. Subscribe to my free newsletter: https://t.co/psB7XxB2Y4.

[Michael Dotaona @borderlogix_md]

@AndrewBolis AI

[Michael Dotaona @borderlogix_md]

@Heistedxyz 🇵🇬 needs to be #heisted. yumi go! (let's go!)

[Michael Dotaona @borderlogix_md]

@Heistedxyz Heist special

[Michael Dotaona @borderlogix_md]

@HeistedFDN @Heistedxyz Redeem

[Michael Dotaona @borderlogix_md]

@Heistedxyz what's the hold up - time to heist💰💰

[Michael Dotaona @borderlogix_md]

@JulianGoldieSEO Agent

[Michael Dotaona @borderlogix_md]

@JulianGoldieSEO Agent OS

[Michael Dotaona @borderlogix_md]

@JulianGoldieSEO agent OS

[Nav Toor @heynavtoor]

10 GitHub repos that automate real work while you sleep in 2026.

Bookmark this list.

1. OpenHands
Autonomous coding agent. 76,500 stars. Used by engineers at Apple, Google, Amazon, Netflix, and NVIDIA.
Repo → https://t.co/kqap76TDuB

2. Hermes Agent
Nous Research dropped this in February. 191,000 stars in three months. Self-improving personal AI.
Repo → https://t.co/OMgRfKAts4

3. CrewAI
Multi-agent workflows that ship real work. Used by 60% of Fortune 500.
Repo → https://t.co/0xohE065sD

4. Aider
AI pair programmer in your terminal. Auto-commits clean diffs. Indie devs ship 5x faster with it.
Repo → https://t.co/67EsCLF7cu

5. n8n
Open-source Zapier. 400+ integrations. Self-hosted workflows that run forever without subscription fees.
Repo → https://t.co/hdycABGGc1

6. LangGraph
The orchestration backbone every production AI agent runs on in 2026.
Repo → https://t.co/bzVBn9uecV

7. Cloudflare Agentic Inbox
Self-hosted email client with a built-in AI agent that reads your inbox and drafts replies.
Repo → https://t.co/Q5RNX2334x

8. Browser Use
98,000 stars. Agents navigate the web, fill forms, scrape data, book meetings.
Repo → https://t.co/h38CvHr83e

9. awesome-mcp-servers
The catalog of every tool your agent can plug into. GitHub, Slack, Linear, Stripe, Postgres, Notion.
Repo → https://t.co/ejVOgkRJDX

10. claude-task-master
Multi-agent task orchestration on top of Claude Code. Turn one prompt into a team shipping a feature while you sleep.
Repo → https://t.co/0xYzJpSX4z

Save this.

100% free. 100% open source.

[AI Edge @aiedge_]

Hermes x Obsidian is the most powerful AI memory system available right now.

Use Obsidian to store all your notes, and Hermes feeds on that data to self-evolve over time.

Your agent learns all your personal goals and context and uses them to build automations for your entire life.

Here's how to set it up in <5 minutes:

Step 1. Download Obsidian

Head to obsidian dot md and download the app.

Create a new vault (this is where all your notes will live locally on your machine).

Start dumping everything in here:

- Meeting notes
- Ideas and goals
- Research and insights
- Journal entries
- Any data you want your AI to know

The more you put in, the more powerful it gets.

Step 2. Connect Hermes to your Obsidian vault

Open the new Hermes desktop app and paste this prompt:

"I want to connect you to my new obsidian vault and have you act as my second-brain orchestrator - do everything necessary to set up that connection now."

This gives Hermes direct access to everything inside your vault.

Step 3. Let it self-evolve

Every time you add a new note, Hermes automatically ingests it.

Over time, it builds a living, breathing memory of everything you know, think, and work on.

Pro tip: Once Obsidian is connected to your agent, you can just prompt it directly to add notes/context/data.

This is what a true AI second brain looks like.

Save this and build your second brain system now.

[Michael Dotaona @borderlogix_md]

@eng_khairallah1 Thank you. I'll use this for my import/export customs clearance workflow. 🇵🇬

[Michael Dotaona @borderlogix_md]

@AlfieJCarter Agents

[Michael Dotaona @borderlogix_md]

@itsalexvacca repo

[Katie Miller @KatieMiller]

Britain is importing future voters and forever sanctioning the brutality of these migrants on their women and girls.

[Promethean Action @PrometheanActn]

"The death of the old model of the world is shocking and traumatic."

That's Obama's former political director, in Toronto this weekend, admitting the empire's model is dead. @SJKokinda on what they're trying to replace it with — and why it won't work.