Archive
Every report we have published
10reports 3,403sources read 248receipts attached
All 10 reports
August 2026 10 reports
26 Aug The LLM Edge in Finance Is a Division of Labor Language models can widen a financial system's field of view. That does not make them universal forecasters, portfolio managers, or sources of alpha. 25 Aug Can This Checkpoint Still Learn? Why retention and future learnability need separate tests in repeatedly trained neural networks. It frames a three-arm choice: continue, reset training state, or retrain from scratch. 24 Aug The Memory Was Right. The Decision Was Wrong. Long-running agents need more than accurate retrieval: they need a disciplined way to turn past events into current, scoped, independently supported inputs to action. 23 Aug How SPADE turns self-generated worlds into a bounded training loop A model can improve without human-written QA pairs or stronger-teacher demonstrations. SPADE shows where the missing supervision moves—and which controls must govern the result. 22 Aug How a Reasoner Learns When to Stop A full-parameter stop/refine policy learns from both repair and damage; sampling, search, and external verification remain isolated experiments around that control. 21 Aug How to Full-Train a Distilled Reasoning Model Without Making It Worse A verified teacher answer is an endpoint, not a training plan. The practical unit of reasoning transfer is a full run whose data, objective, student-generated states, and retention gates are all matched to the student. 20 Aug What Stops Working Before the Million-Token Window Runs Out The million-token window is a serving and pricing limit, not a measurement: literal lookup held in the one pilot to test a full million; nearly everything harder yet measured degrades far earlier. 20 Aug LoRA vs. Full Fine-Tuning in 2026: What Survived the Re-Measurement Two 2024 results anchored how practitioners chose between LoRA and full fine-tuning: "LoRA learns less and forgets less," and the warning that even matched benchmark scores hide structurally different solutions — an "illusion of equivalence." Between 2025 and 2026 both were re-measured, and the answer split by training regime. In supervised fine-tuning the canon survives, but its conditions have been rewritten in terms of adapter capacity, adapter placement, and learning rate. In reinforcement-learning post-training, LoRA now matches full fine-tuning at ranks as low as one — a result the canon never anticipated, resting so far on a lab blog and its reproductions rather than peer review. And three parts of the 2024 answer were never re-tested at all: the effective-rank mechanism offered to explain the gap, the canon's continued-pretraining protocol on current models, and any parity comparison on mixture-of-experts architectures. 20 Aug The Skill Is Real, the Ritual Is Not Yet Measured Curated skills measurably improve coding agents where they carry procedure the model lacks; the process disciplines the frameworks sell remain unmeasured — and the nearest tests lean the other way. 18 Aug Hard, Verifiable Agent Data: Download for Code, Build for the Rest Distillation-grade agent tasks are download-ready where checkers ship with them — code, and now terminal work; everywhere else the verifier is the scarce component, and the environment is yours to build.