← All parts of this equation

Equation 11 · Part 1 · What Alignment Actually Costs

Symbol ρ

ρ  =  CRLCpre\rho \;=\; \frac{C_{\mathrm{RL}}}{C_{\mathrm{pre}}}
ρ\rho

What this part means

ρ is part of the quantity the equation computes from the expression on the right.

Its job in the formula

ρ is part of the quantity the equation computes from the expression on the right.

The passage around this formula

…InstructGPT’s, and it is worth being precise that this is an independent analyst’s estimate resting on assumed GPU pricing and utilisation, not a cost figure DeepSeek itself disclosed. Two data points three years apart, ρ\rho ≈\approx 0.018 for InstructGPT and ρ\rho ≈\approx 0.17 to 0.19 for DeepSeek-R1, describe a ratio that has grown roughly tenfold. Epoch AI’s broader analysis of post-training compute trends confirms the direction independently of any single model: reasoning-focused post-training compute has scaled…

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.