Collinear AI’s Blog
Subscribe
Sign in
Home
Archive
About
Introducing Collinear Simulations: Steerable Personas for AI Agent Testing
TraitBasis, inspired from mech intrep, gives high-fidelity user personas for comprehensive agent testing
Oct 7, 2025
•
Meghana A Rajeev
,
Tsach Mackey
,
Muyu
,
Anand Kumar
, and
Nazneen Rajani
2
Latest
Top
Discussions
We gave Claude, Gemini and GPT, $250k, and it didn't go as you’d expect...
Introducing YC Bench: The first open-source, long-horizon benchmark with a simulation clock
Mar 5
•
Muyu
and
Anand Kumar
6
Collinear Newsletter #9 – Notes on Frontier AI
Hi AI innovators,
Dec 19, 2025
•
Soumyadeep Bakshi
and
Nazneen Rajani
5
RL Infrastructure for AI Agents: Why Environment-as-a-Service is the Missing Piece
Reinforcement learning for large language models is more of a systems problem than ML.
Nov 18, 2025
•
Nazneen Rajani
3
1
Announcing Spider: a lightweight tool to craft post-training data recipes
TL;DR Spider is a single client interface that turns messy distillation and ablation experiments into a simple, configurable workflow.
Nov 6, 2025
•
Soumyadeep Bakshi
6
Collinear Newsletter #8 – Notes on Improving AI
Hi AI innovators,
Nov 4, 2025
•
Soumyadeep Bakshi
8
The case for simulations
Unlocking model uplift through better evaluations
Oct 23, 2025
•
Soumyadeep Bakshi
and
Grant Griffith
6
Through the Valley of Reasoning: What Small Models Teach Us About Learning
NeurIPS paper on knowledge distillation scaling laws for small foundation models
Oct 9, 2025
•
Muyu
,
Tsach Mackey
,
Anand Kumar
,
Meghana A Rajeev
, and
Nazneen Rajani
1
See all
Collinear AI’s Blog
Building the Enterprise AI Improvement Data Flywheel
Subscribe
Collinear AI’s Blog
Subscribe
About
Archive
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
