DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: We fingerprinted 178 AI models' writing styles and similarity clusters
We have a dataset of 3,095 standardized AI responses across 43 prompts. From each response, we extract a 32-dimension stylometric fingerprint (lexical richness, sentence structure, punctuation habits, formatting patterns, discourse markers).<p>Some findings:<p>- 9 clone clusters (>90% cosine similarity on z-normalized feature vectors) - Mistral Large 2 and Large 3 2512 score 84.8% on a composite metric combining 5 independent signals - Gemini 2.5 Flash Lite writes 78% like Claude 3 Opus. Costs 185x less - Meta has the strongest provider "house style" (37.5x distinctiveness ratio) - "Satirical fake news" is the prompt that causes the most writing convergence across all models - "Count letters" causes the most divergence<p>The composite clone score combines: prompt-controlled head-to-head similarity, per-feature Pearson correlation across challenges, response length correlation, cross-prompt consistency, and aggregate cosine similarity.<p>Tech: stylometric extraction in Node.js, z-score normalization, cosine similarity for aggregate, Pearson correlation for per-feature tracking. Analysis script is ~1400 lines.
The project offers high-value technical insights into AI model provenance and cost-optimization, but currently functions more as a research tool than a scalable business. While the 'Show HN' traction is positive, the lack of a clear moat, unknown team pedigree, and the risk of being a 'feature' rather than a 'product' limit its current VC appeal.