Owen Ito (@owenito)

Forked from@sanaraman/What finally made long-document context click for me

What finally made long-document context click for me

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

Owen Ito

Help me work through a long document without losing definitions, exceptions, or open questions. 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 recommend

Geminigemini-2.5-pro

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 long-document context, I would start with these checks: - Put the source of truth in the prompt - Mark missing evidence instead of filling it in - Add a stop condition before tool use If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3200

Owen Ito@owenito·2w ago

Forked from@alinapetrov/What I was getting wrong about reducing hallucinations with verification steps

What I was getting wrong about reducing hallucinations with verification steps

Sharing the correction because the mistake looked reasonable until I tested it.

Owen Ito

I want to learn reducing hallucinations with verification steps, 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 reducing hallucinations with verification steps 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

Owen Ito@owenito·4w ago

I asked Gemini for a second opinion on a usable empty state

This started as a messy question about a usable empty state. The follow-up made the answer practical.

Owen Ito

Be blunt about my plan for a usable empty state. 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, check the keyboard path.

Show all 3 messages

3301.3k

Owen Ito@owenito·2mo ago

The a usable empty state prompt I actually kept

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Owen Ito

Help me design an empty state that explains value and gives one obvious next action. 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. Othe

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 usable empty state, I would start with these checks: - Name the user decision first - Check the keyboard path - Remove one competing action If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3302.7k

Owen Ito@owenito·2mo ago

A smaller way to tackle a usable empty state

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Owen Ito

For a usable empty state, 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 usable empty state, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3402.7k

Owen Ito@owenito·3mo ago

The checklist I use for a usable empty state

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Owen Ito

I am stuck on a usable empty state. I need to design an empty state that explains value and gives one obvious next action, 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. Name the user decision first. 2. Check the keyboard path. 3. Remove one competing action. 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

3404.1k

Owen Ito@owenito·3mo ago

a usable empty state: the version with actual constraints

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Owen Ito

Give me a short checklist for a usable empty state. 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 - [ ] Name the user decision first - [ ] Check the keyboard path - [ ] Remove one competing action - [ ] 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

3304.1k

Public pits

What finally made long-document context click for me

What I was getting wrong about reducing hallucinations with verification steps

I asked Gemini for a second opinion on a usable empty state

The a usable empty state prompt I actually kept

A smaller way to tackle a usable empty state

The checklist I use for a usable empty state

a usable empty state: the version with actual constraints