Write a crochet pattern from a photo with ChatGPT and Claude (gave up)
Copy the prompt below and paste it into the AI tool named on this page.
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Here's a photo of a small crocheted dog I love but can't find a pattern for. Write me a beginner-friendly amigurumi pattern to make it, with stitch counts for each round and every body part.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Find or draft a crochet pattern for a toy in a photo, and be honest about how reliable it is. Questions to ask me first: - What yarn weight and hook size do you plan to use, and how big should it be? - How experienced are you: beginner, intermediate, or confident adjusting patterns? - Would a similar existing pattern be OK instead of an exact copy? Inputs (fill in or confirm): - Photo: [PHOTO] - Yarn and hook: [YARN / HOOK] - Finished size: [SIZE] - My level: [LEVEL] Rules: - First, list every part you can see (head, body, ears, tail, legs, nose and so on) so nothing is missed. - Use bullet points with round-by-round stitch counts, and check each round's count adds up. - Say clearly that a pattern drafted from a photo is a starting point and will probably need adjusting. - Suggest search terms for similar published patterns, since a tested pattern may work better. Checkpoint: Show me the parts list and rough proportions and wait for me to compare them with the photo before writing stitches. If you get stuck: If a shape is irregular and you can't work out the stitches, say so rather than guessing, and suggest a tested pattern for that part. Verify before you finish: Recount the stitches in every round and confirm every part in the parts list has instructions. Output: A parts list, a bulleted round-by-round pattern, assembly steps and a note on what to test first. Done when: I have a pattern that covers every part, or a tested pattern to buy instead.
AI tools
Outcome
Melissa Warr wanted to crochet a Valentine's dog from an image found online, but couldn't find a pattern for it and had never written one. Basic prompts for a pattern from a picture didn't work, so Warr had ChatGPT help write a better prompt. The patterns kept coming out as numbered lists instead of bullet points, with arms and legs that weren't long enough. Warr ran the prompt in both ChatGPT and Claude; Claude's results were better but 'missed many of the parts (the tail, ears, etc.)', and both struggled with irregular shapes. Warr gave up on the AI pattern and bought a pattern on Etsy instead.
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Known limitations
FailureThe source says the AI did not get the job done.
What went wrong: Neither ChatGPT nor Claude produced a usable pattern. Warr gave up and bought a pattern on Etsy.
Source
- Posted
- by Melissa Warr (Capricious Connections)
- Last checked
- Method:
- How we verify
Related cases
Research a Victorian-born grandfather's life with Claude, ChatGPT and Gemini deep research (partial)
Dan Taylor-Watt gave Claude, ChatGPT and Gemini the same brief, with deep research turned on, to research a paternal grandfather, Cecil, who died in 1960, starting from a Word document written by Taylor-Watt's father. Claude took about 6 minutes, used 340 sources and wrote an 11-page, 4,219-word report; it found no significant new information but flagged inaccurate dates, and it later made a 3-minute-30-second narrated video using code and an open-source voice model. ChatGPT took 9 minutes, ran 714 searches and wrote 14 pages (4,659 words); it caught an error about the year of the fire that destroyed service records, noted that the LNER railway wasn't created until 1923, found information on the first wife's family, and spotted a Lance-Corporal's chevron in a photo, but its video attempt fell short. Gemini wrote the longest and most visual report (5,347 words), but its maps were wrong (Osmotherley is east, not south, of Northallerton), it missed the date problems, and it said it couldn't make a video.
PersonalClaudeChatGPTGeminiPartialRecreated promptEvidence: Article or interviewView CaseNarrow 350 direct-admission nursing programs to a college list of 18 with Claude and ChatGPT
Melissa Danielli's daughter wants to be a nurse and get direct admission to a nursing program. Danielli paid $85 to the organizer of a Facebook moms' group for a spreadsheet of 350 schools with their requirements, and the family cut it to 50 by region. Working on two computers, one with Claude and one with ChatGPT, they built spreadsheets, ruled out schools that didn't fit (including ones the AI judged a poor fit) and compiled a final list of 18 schools in a couple of hours one evening.
PersonalClaudeChatGPTWorkedRecreated promptEvidence: Article or interviewView CaseCompare five homeowner's insurance quotes with ChatGPT and Claude, and learn to check insurers' financial ratings, not BBB
Natasha Hsi got five homeowner's insurance quotes for a complicated house. They differed on exclusions, wind and named-storm deductibles, and admitted versus surplus-lines insurers, and Hsi found them hard to follow. They fed all five plus their current renewal into ChatGPT and Claude and ran scenarios such as a hurricane loss and a total loss. When Hsi suggested starting with BBB ratings, both pushed back: BBB tracks complaints, while financial strength ratings show whether an insurer can pay after a storm. Hsi took the questions back to their original agent, who returned a better-structured quote at a more reasonable cost with none of the weakly rated insurers.
PersonalChatGPTClaudeWorkedRecreated promptEvidence: Described by posterView Case