I document my notes and writings on AI research, LLMs, and engineering here. A mix of long-form posts hosted on this site and selected external articles.
A living review of Jev and open System One decision models: calibration, RLCD, evidence quality, open models and methods, benchmarks, applications, failure modes, and the boundary between bounded decisions and generative reasoning.
How alignment changes when language models become long-horizon agents: the 2026 OpenAI–Hugging Face incident, GPT-6 Astra, chain-of-thought monitoring, model–harness–environment co-design, multi-agent risk, and the research agenda ahead.
A frontier-lab loop is three tests wearing one name: your research record gets you seen, technical fluency gets you through, and a third body of unglamorous work decides what you walk away with. Seven technical buckets, with worked code.
A stage-by-stage field guide to LLM training data — what counts as one example and who certifies it at each stage, how synthesis and verification actually work, and how to distill from frontier teachers into a small model.
What OpenAI's booth Q&As at ICML 2026 add up to: the operating horizon is the new scaling axis, and evaluation latency, credit assignment, monitoring, and trust are what it drags along.
How next-generation agents should route deployment experience across context, memory, harnesses, weights, and the learning mechanism itself.
How agents improve the software around a frozen model — the no-gradient twin of environment scaling. The propose-evaluate-select-archive loop, the five surfaces people evolve, the LLM-as-optimizer zoo, and why task supply and verifier honesty are the real bottlenecks, for code agents (SWE-bench, Terminal-bench).
A 2026 field guide to the frontier-LLM training pipeline — data, pre-training, post-training (RL), evaluation, and safety — synthesizing the MAI-Thinking-1, DeepSeek, Qwen, Kimi, Llama, GLM and other technical reports.
An inference-time guide to uncertainty quantification and confidence calibration for long-horizon LLM agents: measuring trajectory uncertainty, acting on it (abstain, ask, reflect, route), and evaluating it — across tool-use, coding, and deep-research agents.
A concept-first interview guide to RL for LLM post-training and agents, from PPO/GRPO/DPO and RLVR to environments, evaluation, and systems consistency.
A pedagogical tour of how the LLM-agent community turns environments into scalable, verifiable RL training signal — the recurring pipeline, the design axes, and the open challenges.
Deep Research is about understanding, reasoning, and synthesis—combining adaptive planning, retrieval, analysis, and context engineering to produce long-form, well-cited research outputs. This article explores how Enterprise Deep Research bridges internal knowledge and external insights to serve strategic business goals.
A novel approach to enhancing Large Language Models through synthetic knowledge ingestion, presented at EMNLP 2024 from Intuit AI Research.
Our work on document enhancement using diffusion models, presented at WACV 2024 from Intuit AI Research.
An interactive framework for cost-effective fine-tuning of language models with sparse human supervision, presented at NeurIPS 2023.
Reliable hallucination detection in black-box language models via semantic-aware cross-check consistency (SAC³), accepted by EMNLP 2023.