Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never
Self-improving AI agents are designed to learn from their mistakes. We show they can also hallucinate mistakes that never happened. We study this failure mode in automated harness optimization, where an LLM-based proposer edits an agent's s
https://arxiv.org/abs/2607.13083v1 ↗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
agents, llm, 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
▸ Add / edit details
Correct facts used on the next screening or memo.
People
S
Su Wang
1.0
low confidence
P
Pin Qian
1.0
low confidence
Y
Yifan Lin
1.0
low confidence
J
Jingzhou Xu
1.0
low confidence
Y
Yihang Chen
1.0
low confidence
X
Xiaochong Jiang
1.0
low confidence
L
Lifei Liu
1.0
low confidence
H
Haoran Yu
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
ReasonBlocks
· Active
The runtime layer that makes AI agents cheaper and more reliable
founders not scraped yet
Parahelp
· Active
The AI agent that resolves complex support tickets, effortlessly
founders not scraped yet