← back

Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD

Large language models have made strong reasoning gains through supervised fine-tuning, reinforcement learning, and on-policy distillation, yet these post-training methods are usually evaluated only by final-answer accuracy. We study how the

https://arxiv.org/abs/2607.13753v1 ↗
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)

TrainLoop · Active
Reasoning Fine-Tuning
founders not scraped yet
hillclimb · Active
Training Data for Recursive Self-Improvement
founders not scraped yet
Mundo AI · Active
High Quality Multilingual Training Data for AI Models
founders not scraped yet
hud · Active
Platform for building RL environments and evals
founders not scraped yet
Nuntius · Inactive
Making Models Follow Rules.
founders not scraped yet