← back

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning th

https://arxiv.org/abs/2607.11475v1 ↗
Thesis fit
Good fit

Within your typical scope; diligence still required.

Edit thesis
In your usual scope
Idea match Light

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)

SafetyKit · Active
AI agents for risk, compliance, and safety
founders not scraped yet
Uplift AI · Active
Foundational Voice Models for regional languages
founders not scraped yet
Kalpa Labs · Active
Scaling Generalist Speech models
founders not scraped yet
Patched · Active
Reliable AI for Regulated Ops
founders not scraped yet
Automorphic · Active
Infuse knowledge into language models with just 10 samples
founders not scraped yet