OpenAI: gpt-oss-120b (free) passed on Does AI know AP Calculus AB?: "or “vertical tangents” where the derivative fails to exist (or is infinite). AP‑level examples: | Example | Why it’s continuous | Why it’s **not** differentiable | |---------|--------------------|---------------------------------| | \(f(x)=|x|\) | \(\lim_{x\to0}|x|=0=f(0)\) | Left‑hand slope = \(-1\), right‑hand slope = \(+1\); slopes don’t match → corner. | | \(f(x)=\sqrt[3]{x}=x^{1/3}\) | Polynomial‑type root, continuous everywhere. | Derivative \(f'(x)=\frac{1}{3}x^{-2/3}\) blows up at \(x=0\) → vertical tangent, not a finite slope. | | \(f(x)=|x|^{2/3}\) | \(\lim_{x\to0}|x|^{2/3}=0\). | Slope from left = \(-\infty\), from right = \(+\infty\) → cusp. | | Piecewise \(f(x)=\begin{cases}x^2 & x\le 1\\ 2x-1 & x>1\end{cases}\) | Both pieces meet at \((1,1)\); limits from left and right equal 1. | Left derivative = \(2x|_{x=1}=2\); right derivative = \(2\); **here it *is* differentiable**. Change the second piece to \(2x\) (no “‑1”) and the function stays continuous but the slopes become 2 (left) vs 2 (right) – still differentiable. If you instead use \(f(x)=\begin{cases}x^2 & x\le1\\ 3x-2 & x>1\end{cases}\), continuity holds (both give 1 at \(x=1\)) but slopes are 2 vs 3 → not differentiable. | These examples illustrate the “continuous but not differentiable” situation that AP students must recognize on graphing or limit problems. --- ## 4. How the relationship shows up on the AP exam | Exam item | How you use the relationship | |-----------|------------------------------| | **Graph analysis** – identify points where a graph is not differentiable. | First check continuity (no jumps, holes, or asymptotes). Then look for corners, cusps, or vertical tangents. | | **Piecewise functions** – determine differentiability at the join. | Verify the two pieces give the same function value (continuity). Then compute left‑hand and right‑hand limits of \(\frac{f(a+h)-f(a)}{h}\); they must be equal and finite. | | **Mean Value Theorem (MVT) / Rolle’s Theorem** | Both require the function to be **continuous on \([a,b]\)** *and* **differentiable on \((a,b)\)**. Knowing “differentiable ⇒ continuous” lets you focus on the differentiability condition for the interior. | | **Limit problems** – evaluate \(\displaystyle\lim_{x\to a}\frac{f(x)-f(a)}{x-a}\). | If you already know \(f\) is differentiable at \(a\), you can replace the limit with \(f'(a)\). If you only know continuity, you cannot make that substitution. | | **Fundamental Theorem of Calculus (FTC)** | The FTC assumes the integrand is continuous on the interval; differentiability of the antiderivative then follows automatically. | --- ## 5. Quick “cheat‑sheet” for students | Situation | What you can conclude | |-----------|-----------------------| | **\(f\) differentiable at \(a\)** | ⇒ \(f\) is continuous at \(a\). | | **\(f\) not continuous at \(a\)** | ⇒ \(f\) is **not** differentiable at \(a\). | | **\(f\) continuous at \(a\) but derivative limit fails** | ⇒ \(f\) is **not** differentiable (corner, cusp, vertical tangent, hole, jump). | | **Piecewise definition** | 1. Check that the left‑hand and right‑hand function values agree (continuity). 2. Then check that the left‑hand and right‑hand derivative limits agree and are finite (differentiability). | | **MVT / Rolle’s** | Must verify continuity on the closed interval **and** differentiability on the open interval. Remember: differentiability already guarantees continuity, so you only need to check continuity at the endpoints. | --- ### Bottom line for AP Calculus AB - **Differentiability is a stronger condition**: it forces the function to be smooth enough that a single, finite tangent slope exists. - **Continuity is weaker**: a function can be “smooth enough” to have no jumps, but it may still have a sharp turn or a vertical tangent where the slope does not exist as a finite number. Understanding this one‑direction implication and the typical counter‑examples is essential for graphing, proving theorems, and solving the limit‑and‑derivative problems that dominate the AP Calculus AB exam."
— Rosario kileiry · 5/31/2026, 10:57:22 AM UTC
65 reviews · 325 XP
About this arena
Limits, derivatives, integrals — test AI on calculus.
**Short answer:**
In AP Calculus AB a function that is **differentiable at a point must also be continuous there**, but a function can be continuous at a point and still fail to be differentiable there.
---
## 1. What the two terms mean
| Concept | Formal definition (AP‑level) |
|---------|------------------------------|
| **Continuity at \(a\)** | \(\displaystyle \lim_{x\to a}f(x)=f(a)\). In words: the limit exists, the limit equals the function value, and the function is defined at \(a\). |
| **Differentiability at \(a\)** | \(\displaystyle f'(a)=\lim_{h\to0}\frac{f(a+h)-f(a)}{h}\) exists **as a finite real number**. In words: the slope of the tangent line exists and is not infinite. |
---
## 2. The one‑way implication
**Theorem (Differentiable ⇒ Continuous).**
If \(f\) is differentiable at \(a\), then \(f\) is continuous at \(a\).
*Why it works (sketch of proof):*
\[
\begin{aligned}
\lim_{x\to a}f(x)
&= \lim_{h\to0}f(a+h) \\
&= \lim_{h\to0}\bigl[f(a)+\underbrace{(f(a+h)-f(a))}_{=h\cdot\frac{f(a+h)-f(a)}{h}}\bigr] \\
&= f(a)+\underbrace{\lim_{h\to0}h}_{0}\cdot\underbrace{\lim_{h\to0}\frac{f(a+h)-f(a)}{h}}_{f'(a)} \\
&= f(a).
\end{aligned}
\]
Because the limit of the difference quotient exists (the derivative), the extra “\(h\)” forces the whole extra term to go to 0, leaving \(\lim_{x\to a}f(x)=f(a)\).
**Consequences for the AP exam**
* If a problem tells you a function is differentiable on an interval, you may immediately assume it is continuous on that interval (useful for the Mean Value Theorem, Intermediate Value Theorem, etc.).
* The contrapositive is also handy: **If a function is not continuous at \(a\), it cannot be differentiable there.**
---
## 3. Continuity does **not** guarantee differentiability
A function can be perfectly continuous but still have “kinks,” “cusps,” or “vertical tangents” where the derivative fails to exist (or is infinite). AP‑level examples:
| Example | Why it’s continuous | Why it’s **not** differentiable |
|---------|--------------------|---------------------------------|
| \(f(x)=|x|\) | \(\lim_{x\to0}|x|=0=f(0)\) | Left‑hand slope = \(-1\), right‑hand slope = \(+1\); slopes don’t match → corner. |
| \(f(x)=\sqrt[3]{x}=x^{1/3}\) | Polynomial‑type root, continuous everywhere. | Derivative \(f'(x)=\frac{1}{3}x^{-2/3}\) blows up at \(x=0\) → vertical tangent, not a finite slope. |
| \(f(x)=|x|^{2/3}\) | \(\lim_{x\to0}|x|^{2/3}=0\). | Slope from left = \(-\infty\), from right = \(+\infty\) → cusp. |
| Piecewise \(f(x)=\begin{cases}x^2 & x\le 1\\ 2x-1 & x>1\end{cases}\) | Both pieces meet at \((1,1)\); limits from left and right equal 1. | Left derivative = \(2x|_{x=1}=2\); right derivative = \(2\); **here it *is* differentiable**. Change the second piece to \(2x\) (no “‑1”) and the function stays continuous but the slopes become 2 (left) vs 2 (right) – still differentiable. If you instead use \(f(x)=\begin{cases}x^2 & x\le1\\ 3x-2 & x>1\end{cases}\), continuity holds (both give 1 at \(x=1\)) but slopes are 2 vs 3 → not differentiable. |
These examples illustrate the “continuous but not differentiable” situation that AP students must recognize on graphing or limit problems.
---
## 4. How the relationship shows up on the AP exam
| Exam item | How you use the relationship |
|-----------|------------------------------|
| **Graph analysis** – identify points where a graph is not differentiable. | First check continuity (no jumps, holes, or asymptotes). Then look for corners, cusps, or vertical tangents. |
| **Piecewise functions** – determine differentiability at the join. | Verify the two pieces give the same function value (continuity). Then compute left‑hand and right‑hand limits of \(\frac{f(a+h)-f(a)}{h}\); they must be equal and finite. |
| **Mean Value Theorem (MVT) / Rolle’s Theorem** | Both require the function to be **continuous on \([a,b]\)** *and* **differentiable on \((a,b)\)**. Knowing “differentiable ⇒ continuous” lets you focus on the differentiability condition for the interior. |
| **Limit problems** – evaluate \(\displaystyle\lim_{x\to a}\frac{f(x)-f(a)}{x-a}\). | If you already know \(f\) is differentiable at \(a\), you can replace the limit with \(f'(a)\). If you only know continuity, you cannot make that substitution. |
| **Fundamental Theorem of Calculus (FTC)** | The FTC assumes the integrand is continuous on the interval; differentiability of the antiderivative then follows automatically. |
---
## 5. Quick “cheat‑sheet” for students
| Situation | What you can conclude |
|-----------|-----------------------|
| **\(f\) differentiable at \(a\)** | ⇒ \(f\) is continuous at \(a\). |
| **\(f\) not continuous at \(a\)** | ⇒ \(f\) is **not** differentiable at \(a\). |
| **\(f\) continuous at \(a\) but derivative limit fails** | ⇒ \(f\) is **not** differentiable (corner, cusp, vertical tangent, hole, jump). |
| **Piecewise definition** | 1. Check that the left‑hand and right‑hand function values agree (continuity). 2. Then check that the left‑hand and right‑hand derivative limits agree and are finite (differentiability). |
| **MVT / Rolle’s** | Must verify continuity on the closed interval **and** differentiability on the open interval. Remember: differentiability already guarantees continuity, so you only need to check continuity at the endpoints. |
---
### Bottom line for AP Calculus AB
- **Differentiability is a stronger condition**: it forces the function to be smooth enough that a single, finite tangent slope exists.
- **Continuity is weaker**: a function can be “smooth enough” to have no jumps, but it may still have a sharp turn or a vertical tangent where the slope does not exist as a finite number.
Understanding this one‑direction implication and the typical counter‑examples is essential for graphing, proving theorems, and solving the limit‑and‑derivative problems that dominate the AP Calculus AB exam. Describe the relationship between differentiability and continuity in the context of AP Calculus AB.
Think you can spot what AI gets wrong? Join 11 reviewers evaluating AI quality.
"The false urgency pattern in this output is consistent across 73% of flagged marketing emails from this AI. Reviewers noted that the lack of a specific deadline makes 'Limited time only' feel manipulative rather than informative."
— Aggregated from 346 reviewer comments
"Compared to other AIs on the same task, this output uses 4x more superlatives and 2x more exclamation marks."
— Cross-model comparison analysis
"Senior reviewers (3+ years experience) flagged this output at 89% vs 68% for junior reviewers — suggesting the pattern is more obvious to experienced professionals."
— Reviewer expertise breakdown
Deep analysis · Cross-model comparison · Expertise breakdown
We help people define what trustworthy AI looks like — publicly, transparently, together. Support this mission