Rhea Haddad (@rheahaddad)

The useful change was doing a small retrieval check before reading more.

Rhea Haddad

I want to learn writing eval cases before changing a prompt, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain writing eval cases before changing a prompt in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6100

Rhea Haddad@rheahaddad·2w ago

Forked from@emilnovak/I finally found a good way to learn reading uncertainty in a dashboard

I finally found a good way to learn reading uncertainty in a dashboard

The useful change was doing a small retrieval check before reading more.

Rhea Haddad

I want to learn reading uncertainty in a dashboard, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

ChatGPTgpt-5

Good. Do these without looking anything up: 1. Explain reading uncertainty in a dashboard in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6100

Rhea Haddad@rheahaddad·2w ago

I asked Gemini for a second opinion on a small CLI people can trust

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Rhea Haddad

Be blunt about my plan for a small CLI people can trust. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

Geminigemini-2.5-pro

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, keep the patch smaller than the diagnosis.

Show all 3 messages

340613

Rhea Haddad@rheahaddad·1mo ago

Forked from@mateochen/I asked Gemini for a second opinion on structured output that stays readable

The a small CLI people can trust prompt I actually kept

The first answers were broad enough to be useless. This version asks for assumptions, evidence, and a next step.

Rhea Haddad

Help me design a command-line tool with dry-run, clear errors, and idempotent behavior. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change your recommendation. O

ChatGPTgpt-5

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For a small CLI people can trust, I would start with these checks: - Reproduce the failure before changing code - Keep the patch smaller than the diagnosis - Write the rollback before deployment If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

340499

Rhea Haddad@rheahaddad·2mo ago

A smaller way to tackle a small CLI people can trust

I wanted help with a small CLI people can trust without pretending the model knew facts I had not provided.

Rhea Haddad

For a small CLI people can trust, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

ChatGPTgpt-5

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For a small CLI people can trust, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

330556

Rhea Haddad@rheahaddad·2mo ago

The checklist I use for a small CLI people can trust

I kept the useful constraints and dropped the role-play. It works better when the missing details are stated plainly.

Rhea Haddad

I am stuck on a small CLI people can trust. I need to design a command-line tool with dry-run, clear errors, and idempotent behavior, but my current attempt is getting vague and too big. What would you check first?

Claudeclaude-opus-4.5

First, shrink the decision. Do not solve the whole subject at once. 1. Reproduce the failure before changing code. 2. Keep the patch smaller than the diagnosis. 3. Write the rollback before deployment. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages

3302k

Rhea Haddad@rheahaddad·3mo ago

a small CLI people can trust: the version with actual constraints

The first answers were broad enough to be useless. This version asks for assumptions, evidence, and a next step.

Rhea Haddad

Give me a short checklist for a small CLI people can trust. I want something I can run before I call the work done.

Claudeclaude-opus-4.5

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Reproduce the failure before changing code - [ ] Keep the patch smaller than the diagnosis - [ ] Write the rollback before deployment - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages

3403.4k

Rhea Haddad

Public pits

I finally found a good way to learn writing eval cases before changing a prompt

I finally found a good way to learn reading uncertainty in a dashboard

I asked Gemini for a second opinion on a small CLI people can trust

The a small CLI people can trust prompt I actually kept

A smaller way to tackle a small CLI people can trust

The checklist I use for a small CLI people can trust

a small CLI people can trust: the version with actual constraints