1. Become the AI Operator, Not the Bystander

Learn to direct AI tools inside your actual job — prompting, editing, verifying — so you’re running the workflow, not being automated out of it. The tasks most at risk are the ones AI can complete end-to-end without supervision.

2. Sharpen Judgment and Taste

AI can generate a hundred options fast. It can’t tell you which one is right for this client, this culture, this moment. Your ability to evaluate and choose is the scarce skill now — and it gets more valuable, not less, as AI gets smarter.

3. Learn Prompt Engineering as a Real Skill

Not just “how to ask ChatGPT things” — structured thinking: breaking problems into steps, specifying constraints, iterating on output. If AGI does arrive within a few years, the people fluent in directing AI systems will adapt fastest.

4. Specialize in What AI Can’t Fully Model

Deep, idiosyncratic expertise — legal nuance, medical judgment, local market knowledge, a specific craft — is much harder to replace than generalist knowledge work, even by a highly capable general system.

5. Own the Relationship, Not Just the Output

Clients and employers pay for trust and accountability. Someone still needs to be the human who says “I stand behind this” when things go wrong — no AGI timeline changes that.

6. Get Fast at Learning New Tools

Specific AI tools will keep changing, especially if the pace Hassabis describes is real. The future-proof skill is picking up a new tool’s logic quickly and discarding what doesn’t work.

7. Move Upstream: Design Systems, Not Just Tasks

Instead of doing every task yourself, build the workflow or pipeline that produces the work at scale. Systems-thinkers direct AI; task-doers compete with it directly.

8. Build a Reputation AI Can’t Impersonate

AI can mimic style, but it can’t replicate earned credibility or a genuine relationship with an audience. Audience trust and a recognizable voice are durable moats, AGI or not.

9. Use AI to Do More, Not to Do Less

The safest path isn’t “let AI handle it so I can slow down” — it’s “let AI multiply my output so I can take on more ambitious work than before.” If Hassabis is right about the timeline, ambition compounds faster now than ever.

10. Teach or Explain AI to Others

There’s a growing gap between what AI can do and what most people know how to use it for. Translating that capability into practical value for non-experts is itself a durable, in-demand skill — and it only gets more valuable as the technology accelerates.

Worth noting: Hassabis isn’t the only voice in this conversation, and not everyone agrees on the timeline. Some researchers put AGI a decade or more away, and definitions of “AGI” itself still vary widely across the industry. But even the more cautious voices agree the direction is the same — which is exactly why the 10 steps above matter regardless of the exact date.