Tag: ML Engineering

All the articles with the tag "ML Engineering".

• A Repair Can Save a Trajectory Without Teaching the Agent

  14 Aug, 2026 · 18 min read

  An eight-seed counterfactual-replay experiment found that high-value one-action repairs reliably rescue failed agent trajectories—but a repair-value-dominant SFT selector did not beat simpler rules and recovered only 25% of matched-RL improvement.

• A Looped Transformer Router Shows Its First Replicated Gain

  6 Jul, 2026 · 11 min read

  A small-budget BPE language-model experiment where a sparse late-final-loop token-feedback router becomes the first route-looped Transformer candidate to beat matched fixed-loop baselines across several controlled checks.

• Scaling RL for White-Collar Work: The Environment Foundry

  3 Jul, 2026 · 20 min read

  A practical framework for turning common white-collar workflows into RL environments: spreadsheets, CRM tasks, customer support, web research, dashboards, and other software-mediated work.

• When a Looped Transformer Router Almost Works

  1 Jul, 2026 · 12 min read

  A controlled small-scale language-composition experiment comparing fixed and routed looped Transformers, showing why the first sequence-level router was competitive but collapsed toward a weak exit policy.

• Optimizing Inference for Router Looped Transformers

  Updated: 29 Jun, 2026 · 20 min read

  A research note on serving router looped transformers: why normal KV cache semantics break, what latency data says so far, and how vLLM or SGLang could be adapted with route-template batching and virtual-step KV cache.

• How to Test Pretraining Ideas at Small Scale Before Betting on a Large Model

  29 Jun, 2026 · 25 min read

  A practical guide to validating pretraining improvements with small proxy models, scaling ladders, isoFLOP budgets, loss curves, downstream evals, and rank-correlation checks before committing to an expensive large-model run.