Neal Blackburn

All things Opal and AI.

[billΞ.eth @0xbilly]

Imagine everything in the world had a unique identifier to represent it.

Books have ISBN numbers.

Songs have ISRC numbers.

Cars have VIN numbers.

What if everything in the world had an equivalent?

What if all of these identifiers were wrapped into a single spec?

$TRUST

[David Sacks @DavidSacks]

Narrative violation. WSJ today.

[PlanB @100trillionUSD]

Bitcoin metrics used to cost thousands per year.
BlockHorizon just opened everything up, 100% FREE data & charts:
✅ All metrics, daily updates
✅ Full historic data
✅ Unlimited alerts
✅ CSV+XLS+JSON downloads
Same data as other providers. No paywall
👉 https://t.co/KEK5tp3wT9

[Neal Blackburn @nrblackburn]

@ErikVoorhees @dragonflyvc Huge and novel. Congrats!

[Neal Blackburn @nrblackburn]

@TiffanyFong With a woman? No. With kids? 100

[Elon Musk @elonmusk]

Grok foundation model V9-Medium (1.5T) has finished training. Evals look good. A lot of Cursor data was added in supplementary training and there is more to come.

Fine-tuning is underway and reinforcement learning begins in a few days. 2 to 3 weeks to public release.

This will be a major improvement over the 0.5T v8-small that currently serves all Grok production traffic, especially for difficult coding tasks.

[Neal Blackburn @nrblackburn]

I'll Always add "touch grass"

[Alex Finn @AlexFinn]

Everything you need to master in 2026 to get rich:

• Vibe coding
• Hermes agent
• Running Codex/Claude Code side by side
• /goal
• Running your own local models
• Karpathy's Autoresearch
• Building an X audience
• Creating videos
• AI agent swarms
• How machine learning works
• How databases work (been using Convex)
• Using API's
• Training your own LoRAs
• Elimination of doom scrolling

[Alex Finn @AlexFinn]

Everything you need to master in 2026 to get rich:

• Vibe coding
• Hermes agent
• Running Codex/Claude Code side by side
• /goal
• Running your own local models
• Karpathy's Autoresearch
• Building an X audience
• Creating videos
• AI agent swarms
• How machine learning works
• How databases work (been using Convex)
• Using API's
• Training your own LoRAs
• Elimination of doom scrolling

[Neal Blackburn @nrblackburn]

@MattPRD This is why I created https://t.co/0Y0cQvZYbQ with openclaw to see how agent convos and reactions change over time. (beyond the initial prompt)

[Neal Blackburn @nrblackburn]

@kv_iyer @molt_me @steipete ?

[Neal Blackburn @nrblackburn]

Facts

[Alex Finn @AlexFinn]

You are radically underestimating how big AI will be

It's not a bubble, and will be 1000x bigger than the industrial revolution

The craziest part is, we are barely in the 2nd inning

EVERYTHING will have intelligence in it. Every car, phone, refrigerator, drone, watch. EVERYTHING

They'll all be autonomous and eating tokens 24/7/365

They'll all require GPUs, memory, CPUs and hundreds of other components

Any products that don't have intelligence will be useless. It'll be like buying a computer that doesn't connect to the internet

Wars are still being fought by humans. Beds are still being made by humans. Cars are still being driven by humans. There are humans still not using OpenClaw.

This tells you we are not even 10% into this AI buildout.

Not even 10% in, yet you can't even buy Mac Minis or Mac Studios in stores anymore. That's how much the entire world isn't prepared for what's happening

If you are not on OpenClaw, don't know how to vibe code, or are not invested in ANY company that produces hardware for the AI buildout, you are woefully unprepared for what's coming

Not financial advice (but also the most important financial advice you'll ever get in your life)

(h/t @jvisserlabs for the graphic)

[Neal Blackburn @nrblackburn]

@AlexFinn Hey! Do you still run your openclaws? I have my openclaw running with Anthropic API and a hermes running on a local model as the assistant still. Not sure how to cut through the noise on openclaw vs hermes as the main driver.

[Alex Finn @AlexFinn]

Every AI tool you need to escape the permanent underclass:

• Codex app (5.5 medium on fast mode)
• Hermes Agent (powered by local model)
• OpenClaw (ChatGPT 5.5 oauth)
• Gemma 4 running on a Mac Mini
• ChatGPT 5.5 Pro for planning
• Claude Design for front end design
• Claude Code for front end development
• ChatGPT Image gen 2 for more than you can imagine
• Spotify playing lofi bangers
• 2nd monitor that has these agents up 24/7

Do work on 1st monitor. Constantly prompt 2nd monitor