DNDuane Nielseninproximal.hashnode.dev·Apr 26 · 14 min readThe Building Blocks of an Agent Memory SystemThe Building Blocks of an Agent Memory System Most agent "memory" systems retrieve too much. They paste the last N turns into the context window, or they dump the top-K results from a vector search, and they hope the model finds the signal. The model...00
DNDuane Nielseninproximal.hashnode.dev·Feb 5 · 4 min readSmaller is Better: Replacing GPT-4o-mini with a 7B Local JudgeI expected the 30B model to be the better judge. It wasn't. When I set out to replace OpenAI's GPT-4o-mini as the judge for the Oolong benchmark, my plan was simple: use the biggest local model I had. Qwen3-coder at 30B parameters seemed like the obv...00
DNDuane Nielseninproximal.hashnode.dev·Jan 18 · 11 min readHow InfoNCE Creates Exploration: The Hidden Engine of Contrastive RLA personal exploration of the mechanisms behind emergent exploration in goal-conditioned reinforcement learning Contrastive RL made a huge splash at NIPS 2025, with "1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reach...00
DNDuane Nielseninproximal.hashnode.dev·Jan 9 · 8 min readContrastive RL: A Step-by-Step Guide to Learning ReachabilityThe paper "1000 Layer Networks for Self-Supervised RL" won Best Paper at NeurIPS 2025, and for good reason. It demonstrates that goal-conditioned RL can scale to 1000-layer networks—something previously thought impractical. But the real insight isn't...00
DNDuane Nielseninproximal.hashnode.dev·Jan 6 · 5 min readHow wp.ScopedTimer Found My 12x SpeedupI was benchmarking a gridworld RL environment built on NVIDIA Warp. The native Warp version hit 8.4 million world-steps per second on small grids - impressive. But when I wrapped it with JAX for compatibility with standard RL training pipelines, perf...00
