Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclos
https://arxiv.org/abs/2607.14345v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
llm
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 → stable
▸ Add / edit details
Correct facts used on the next screening or memo.
People
J
Jan Betley
2.0
low confidence
J
Johannes Treutlein
2.6
low confidence
J
Jan Dubiński
2.0
low confidence
H
Harry Mayne
2.0
low confidence
K
Karol Gałązka
2.0
low confidence
N
Niels Warncke
2.0
low confidence
A
Anna Sztyber-Betley
1.0
low confidence
O
Owain Evans
2.0
low confidence
A
Anna Sztyber
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Automorphic
· Active
Infuse knowledge into language models with just 10 samples
founders not scraped yet
Emre Murray Mangir
Joseph Metzinger
Luel
· Active
Turning everyday words and actions into usable training data.
founders not scraped yet