What students report
Review sample
- Freshman150%
- Alumni150%
Student voice
Why students feel that way
Patterns tell us what is happening. Student accounts explain why.
Distinctive themes
No distinctive review themes have cleared the evidence threshold yet.
Representative perspectives
Ethan LeeIf you like thinking about logic and enjoy solving problems, this is for you.
Enjoyment & fit
hard very hard hard LM-generated code is more reliable than LLM-generated instructions.** A prompt that says "never generate img tags" is a suggestion. A Python function that strips img tags and returns a validation error is a…
Difficulty & workload
Compare schools
- Career outlook
- 3.9
- Enjoyment
- 3.8
- Recommend
- 88%
- Career outlook
- 3.6
- Enjoyment
- 4.0
- Recommend
- 80%
- Career outlook
- 3.1
- Enjoyment
- 3.7
- Recommend
- 80%
- Career outlook
- 3.1
- Enjoyment
- 3.6
- Recommend
- 77%
- Career outlook
- 3.4
- Enjoyment
- 3.5
- Recommend
- 77%
- Career outlook
- 4.0
- Enjoyment
- 3.9
- Recommend
- 92%
Similar majors at CMU
Complete evidence
Student reviews
2 reviews
Ethan Lee · AlumniIf you like thinking about logic and enjoy solving problems, this is for you.
hard very hard hard LM-generated code is more reliable than LLM-generated instructions.** A prompt that says "never generate img tags" is a suggestion. A Python function that strips img tags and returns a validation error is a guarantee. The most impactful part of Sentinel isn't the detection or the eval — it's the moment where it stops trying to convince the LLM to behave and just writes code to enforce it. - **Observability for AI agents is fundament
Add context
Studied Computer Science at CMU?
Help future students understand the promise, demands, and tradeoffs of this program.