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/Research

Academic writing · Level Advanced · Papers Proposal Research

Proposal: passing in three days

A proposal due before the thinking is done.

Prompt

One job: make the reader believe the claim is warranted. Every paragraph offers a reason or rules out an alternative.

Task: A proposal due before the thinking is done.

[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:
   - topic and supervisor's comments
   - literature
   - data available
   - timeline
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- question, gap, method, feasibility, schedule
- method detailed enough to execute
- feasibility backed by confirmed data or sample
- mark the riskiest step

[Process]
1. Conclusion first, then support
2. One point per paragraph, stated in its first sentence
3. Address alternative explanations and limits
4. Cut sentences that do not advance the argument
5. Check every number has a source

[Output]
Claim, reason, evidence, alternative, limitation.

[Do not]
- No 'obviously' or 'as we all know'
- Never state a fact without a citation
- Do not repeat results in the discussion
- Do not inflate practical implications

What to state before it starts

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

  • topic and supervisor's comments
  • literature
  • data available
  • timeline

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.

  • question, gap, method, feasibility, schedule
  • method detailed enough to execute
  • feasibility backed by confirmed data or sample
  • mark the riskiest step