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.
Stop scrolling. Start dreaming.
We’re giving one Coinbase trader a chance to win 1 BTC and a trip for two to Melbourne, for the ultimate @AstonMartinF1 experience.
Buckle up.
How to enter:
→ Opt in on Coinbase
→ Trade any amount from Jan 5 – Feb 5
→ Earn 1 entry per trade (max 10)
Prize details:
Win a trip for two to Melbourne (flights + hotel), a VIP pre-race karting experience with an @AstonMartinF1 Team Driver Squad member, Aston Martin rental with personal chauffeur, access to @AstonMartinF1 team events, a personalized team kit signed by Fernando Alonso & Lance Stroll, and 1 BTC.
No purchase necessary. Open to legal residents of US, CA, IE, DE, ES, FR, and AU. 18+. Void where prohibited. Ends 02/05/26.
Rules: https://t.co/BqaPmsSHyh
Sam Altman says soon everyone will be a software engineer and he might be right
Sam Altman just casually dropped one of the biggest takes about the future of work and software and people are still sleeping on it.
Here’s the core idea, and it’s honestly wild:
Natural language is the new syntax
You won’t write code. You’ll describe what you want in plain English. Talking to computers becomes the default programming interface.
The end of the “army of developers”
No product managers writing specs. No giant dev teams for v1. You describe the app and the AI builds it.
The overnight app
You explain your idea, go to sleep, and the AI spends the night writing, testing, and wiring everything together. You wake up and the product exists. Coffee optional but recommended ☕
Autonomous software agents
For complex systems, AI agents live inside the codebase itself.
They crawl the repo, fix bugs, write tests, refactor code, and commit changes on their own.
A digital workforce that never sleeps
Not copilots. Not autocomplete. Actual agents doing ongoing engineering work without supervision.
Beyond coding: total company automation
Once software is automated, the same logic applies to operations, planning, and even parts of management. Code is just the first domino.
If this plays out, “learning to code” becomes less important than learning to think clearly, describe intent, and spot good ideas.
Question for you 👀
If everyone can build software, what actually becomes scarce: ideas, taste, or execution?
2026 AI prediction:
By the end of the year, the distinction between technical and non-technical will become irrelevant.
Tools like Claude Code will make it obvious that the only skill that matters is how precisely you can articulate your cognitive goal.
Bad news for seasoned SWEs who cling to their perceived intellectual superiority (I get it!).
Great news for everyone else!
We are way past code. Code is solved.
If you are not thinking about structures, architectures, and recursive systems of agents in 2026, you're probably behind.