Pot să vibecodez WasItAIGenerated?

Ce construiești

Build a private workspace that pastes in text, asks one general model for an AI-likelihood judgement with reasoning, stores results, and exports them.

ce îți trebuie

• OpenAI or Anthropic API key in .env
• Node.js 22
• SQLite database
• A README stating plainly that the output is a guess, not a detector, and must never be used to accuse anyone

The text box is trivial. The trained classifier and its measured false-positive rate are the product.

Promptul

Verdictul e NU CHIAR, iar promptul rămâne oricum: nu înlocuiește aplicația, reconstruiește partea care chiar e cod. Restul e moat-ul.

Build the closest honest consolation tool inspired by WasItAIGenerated. Do not claim it detects AI writing.
Use exactly this stack: Next.js 15 + TypeScript + SQLite.
Primary job: paste text, send it to one general language model, and record that model's opinion on how machine-like the writing reads, with its reasoning.
Start from an empty folder and create the complete working project.
Single-user and private by default; store everything locally.
Put every secret in .env and provide .env.example.
Show the result as an opinion with reasoning, never as a score, a percentage or a verdict - the whole point of this build is that it cannot measure what the paid product measures.
Put a permanent, non-dismissable notice in the UI and the README: this is one model's guess, it has no measured error rate, and it must never be used to accuse anyone of anything.
Include clear empty, loading, validation, success and failure states.
Add export so the user is not trapped in the app.
Accessible keyboard navigation, labels, focus states and sensible contrast.
Deliberately exclude these paid-product advantages: a trained classifier, a labelled corpus, a published false-positive rate, image/audio/video detection, per-sentence attribution.
Do not fake accuracy claims, benchmarks or compliance statements.
Write unit tests for the data model and one end-to-end smoke test of the core loop.
Create a README with setup, architecture, data location and an explicit limitations section.
Run the tests and build before finishing, then fix what fails.

Ce pierzi

• a trained classifier and the labelled corpus behind it
• a measured false-positive rate you can quote to an institution
• detection for images, audio and video, not just text
• per-sentence highlighting instead of one document-level guess
• retraining as generators change

De ce se plătește în continuare

Institutions do not buy a verdict, they buy a defensible one. A university that flags a student needs a documented error rate, an audit trail and a vendor who will stand behind the number. That is a measurement problem, not an interface problem, and it is why every serious buyer in this category asks about false positives before features.

moat: Modele proprietare Date proprietare Conformitate și reglementări ce e un moat

trained classifier, labelled corpus, published error rates

Cine l-a construit deja

Să pornești de aici e tot vibecoding: promptul e pentru când o vrei exact în felul tău.

• Binoculars (se deschide într-o filă nouă) — Zero-shot LLM text detection using perplexity ratios between two models.
• DetectGPT (se deschide într-o filă nouă) — Curvature-based zero-shot detection of machine-generated text.

Ești de acord?

Aplicații similare

GPTZero — NU CHIAR Originality.ai — NU CHIAR Copyleaks — NU CHIAR