Stories by t55

RL Speedrun

Target Policy Optimization

Show HN: Kilroy – Knowledge base for teams using Claude Code

Procedural Reasoning Datasets

In Defence of Gary Marcus

Reasoning Gym – Procedural RL reasoning datasets

ChatGPT Agent [video]

ReasoningGym: Reasoning Environments for RL with Verifiable Rewards

Show HN: Rehearsal.so, Duolingo for Public Speaking

End-to-End Vision Tokenizer Tuning

YC Interview Mock Practice

D1: Scaling Reasoning in Diffusion LLMs via Reinforcement Learning

Are LLMs more than autocomplete? AI Debate

Block Diffusion: Interpolating Autoregressive and Diffusion Language Models

How to stay in flow while using Cursor or Windsurf

Generative Modelling in Latent Space

Show HN: Debate Uncle Bob – Is SQL Dead? (Voice RPG)

OpenAI O3 and O4-Mini

Memory in ChatGPT

Superintelligence startup Reflection AI launches with $130M in funding

1 2