← back

Pretraining Data Can Be Poisoned through Computational Propaganda

Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent t

https://arxiv.org/abs/2607.15267v1 ↗
Thesis fit
Good fit

Within your typical scope; diligence still required.

Edit thesis
In your usual scope
Idea match None

How close the company’s idea is to your thesis statement

Sector ai

Overlap with sectors you care about

Geography Unknown

Location unknown — scores 0

Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”

Founder → stable Traction → stable Idea vs market ↓ declining
Generate memo
Add / edit details

Correct facts used on the next screening or memo.

Similar baseline plays (YC · idea space)

Kiwi Biosciences · Active
Patent-pending enzymes to break down common dietary triggers
founders not scraped yet
Quadrant Health · Active
Analyzing EHR and messaging data to predict disease before it occurs.
founders not scraped yet
Observa · Inactive
Catch accidental database exposures before the bad guys
founders not scraped yet
PostEra · Active
Medicinal Chemistry powered by Machine Learning
founders not scraped yet
sieve · Active
AI + human review to solve data cleaning - accessible via API or Excel
founders not scraped yet