cd /news/ai-startups/i-ran-cosine-similarity-on-every-yc-… · home › topics › ai-startups › article
[ARTICLE · art-142349] src=dev.to ↗ pub= topic=ai-startups verified=true sentiment=· neutral

I ran cosine similarity on every YC startup. 2025 batches are 2.5x more repetitive than 2015

A developer embedded all 6,142 Y Combinator companies with live domains across 48 batches (Summer 2005 through Fall 2026) using text-embedding-3-large at 1024 dimensions and found that 2025 batches are roughly 2.5x more repetitive than 2015. In 2015, one in five companies in a batch had a near twin among earlier YC companies, compared with two in five in 2025, measured by counting batch members whose best cosine similarity against a random sample of 500 earlier companies cleared 0.80. To avoid measuring writing style, the analysis embedded gpt-5-mini summaries generated from rendered homepages and search snippets rather than raw homepage copy.

by read1 min views1 publishedSep 30, 2026

Everyone says every YC startup is now the same AI agent. I ran cosine similarity on all 6,142 of them to see whether that is true, and by how much. In 2015, one in five companies in a batch had a near twin among earlier YC companies. In 2025 it was two in five.

6,142 Y Combinator companies with a live domain, 48 batches from Summer 2005 through Fall 2026. Each one got a vector from text-embedding-3-large at 1024 dimensions.

The catch: I did not embed homepages. Homepage copy varies more by who wrote it than by what the company does, and an embedding of raw copy mostly measures writing style. Instead, gpt-5-mini wrote a five-sentence summary of each company from two inputs, a rendered homepage (ScrapingBee) and search snippets for the domain (Serper). The prompt forces the same five questions in the same order every time: product, buyer, delivery, market, pricing. Same shape of text for a 2008 company and a 2026 one. 206 companies had no usable homepage and fell back to YC's own description; those skew old, so they push against the result rather than for it.

Similarity is cosine between the normalised vectors.

For each company, take its best cosine score against a random 500 companies from earlier batches. Count how many in the batch clear 0.80. Repeat with ten different random 500s and average.

Full analysis and data here: [https://fundingwatcher.com/research/yc-batch-similarity/](https://fundingwatcher.com/research/yc-batch-similarity/)
── more in #ai-startups 4 stories · sorted by recency
── more on @y combinator 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-ran-cosine-similar…] indexed:0 read:1min 2026-09-30 · —