liveBook · Manning

Model scaling

As explained in Vibe Engineering

Model scaling is the practice of increasing model size, training-data volume, and compute to improve model capability.

Model scaling promises that larger models, more data, and more compute will resolve quality and reasoning failures. Capability has risen, but hallucination and the need for external verification have persisted across generations. section 1.2

Use scaling as a capability strategy, not as a substitute for verification:

  • Increasing model size, data volume, and related resources can produce predictable performance gains. section 1.2
  • Benchmark improvements do not eliminate hallucination, because probable next-token predictions can diverge from truth. section 1.2
  • Treat successive releases as iterative refinement and preserve external checks instead of assuming a larger model knows when it is wrong. section 1.2

Capability without reliability

Across the progression from the first GPT systems to current frontier models, reasoning, competitive-programming, and agentic benchmark scores improve while the underlying hallucination failure mode remains. section 1.2

How Vibe Engineering covers it

How deep it goes
Explains benchmark gains, persistent hallucination, and structural limits but stops short of implementation procedures.
Examples
Uses GPT generations, reasoning benchmarks, competitive-programming sets, and SWE-bench to contrast capability with reliability.
What you can do after
Evaluate scaling claims without treating benchmark gains as evidence that verification is no longer necessary.
How it connects
Connects model size, data volume, performance, hallucination, benchmarks, and external verification.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Vibe Engineering. The section links point to the parts of the book it draws on.