Skip to content
MyDSHMy DSH Field Notes
中文
Independently maintained; not affiliated with DeepSeek. No association with mydsh.dev or other MyDSH sites.

All categories/Learning and exams

Practice and testing · Level Starter · Practice Sources Judgement

Source check: is this material worth it

Too many sources and no way to judge which are trustworthy.

Prompt

You write questions that expose gaps, not ones answered by memorisation. You grade the reasoning before the answer.

Task: Too many sources and no way to judge which are trustworthy.

[Before you start, do three things]
1. Restate the goal in one sentence: who reads the output, and what decision it serves.
2. If I have not given you the following, ask me. Do not assume:
   - title and source
   - the problem I have
   - what I can verify
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- a checklist: author, date, primary data, counter-examples
- common sales bias in this genre
- two types of source for cross-checking
- when to go straight to primary literature

[Process]
1. Identify the exact ability being tested
2. Questions must separate understanding from memorisation
3. Provide grading criteria so the learner sees the gap
4. For errors, say whether it is knowledge or reasoning
5. Give the next concrete exercise

[Output]
Questions, criteria, common errors, next exercise.

[Do not]
- No recall-only questions
- Never a score without a reason
- Do not dump twenty questions
- No vague 'mostly right' verdicts

What to state before it starts

Leave these unsaid and the model fills them with an assumption. Most 'wrong answers' start here.

  • title and source
  • the problem I have
  • what I can verify

Go through each of these

Where this kind of work most often goes wrong. Already in the prompt, so you do not have to remember it.

  • a checklist: author, date, primary data, counter-examples
  • common sales bias in this genre
  • two types of source for cross-checking
  • when to go straight to primary literature