Posts
12 posts published between 2024 and 2026, listed newest first.
Recurring subjects: LLM, Blockchain, Prompt Engineering, Survey and Machine Learning.
Fair Ordering: Taming MEV on Ethereum
Maximal Extractable Value comes from a validator freedom to order transactions within a block, and every mitigation approach constrains that freedom differently.
Why GPU Kernel Benchmarks Miss Real Bugs
Passing a correctness benchmark and being correct in production are different claims for LLM-generated GPU kernels — the gap comes down to which inputs get sampled.
Diagnosing Conflicts in RAG Pipelines
Why retrieval-augmented generation fails when context disagrees with parametric knowledge, and a checklist for diagnosing which failure mode you are looking at.
From AutoPrompt to TextGrad: A Prompt Survey
A chronological survey of automated prompt optimization 2020–2025: AutoPrompt, APE, OPRO, EvoPrompt, DSPy, TextGrad, PromptAgent, and how to choose between them.
LLM Prompt Compression: A Practitioner Guide
A practitioner's guide to LLM prompt compression: LLMLingua, GIST Tokens, 500xCompressor, KV-cache methods, and the rate-distortion limits of compressing context.
Prompt Structuring Techniques for LLMs
A chronological survey of LLM prompt structuring: chain-of-thought, the instruction hierarchy, system prompt design, and evaluation frameworks.
Comparing LLM Safety Techniques
A practitioner's survey of LLM safety techniques across OpenAI Harmony, Anthropic Constitutional AI, Google SAIF, Meta Llama Guard, and open-source RLHF frameworks.
Tackling Data Imbalance in Federated Learning
How Fed-Focal Loss addresses one of the most challenging problems in distributed machine learning: handling imbalanced data across federated clients.
The AI Copyright Challenge for Generative AI
As generative AI transforms content creation, we need new frameworks that respect copyright while enabling innovation. Here's how we can build them.
The MEV Problem: Fairer Value Distribution
Exploring Maximal Extractable Value (MEV) in Ethereum and why we need better mechanisms for fair value distribution across the ecosystem.
DePIN: The Future of Physical Infrastructure
Why Decentralized Physical Infrastructure Networks (DePIN) represent a fundamental shift in how we build and own critical infrastructure.
Why Deepfake Detection Needs Decentralization
As deepfake technology becomes more sophisticated, centralized detection approaches are failing. Here's why we need decentralized solutions.