Blog

Blog.

Current personal blog. Technical/AI blog here.

Posts

25 posts

Jun 30, 2026 Mac Power User Finder customizations Cheatsheet
Mac Finder is grossly underconfigured by default for power users. These are some (AI generated) tweaks to customize it. Warning: Some are verified, others are not, so review each one carefully before using.
mac finder poweruser cheatsheet
Jun 29, 2026 Model-ID glossary - every part in model identifiers
A reference that decodes every meaningful stem found in model identifiers across Artificial Analysis, Ollama, and OpenRouter - parameter sizes, quantization/precision formats, runtimes, build-time techniques, capability suffixes, context...
ai llm reference
Jun 29, 2026 Model glossary run 07 - v2 verification
Run 07 of the model-ID glossary analysis - re-researches the four hedged claims in the analysis report (Ollama MLX backend, FP4 in llama.cpp, Apple Silicon FP4/FP8 hardware, MLX long-context decode) with sources.
ai llm quantization
Jun 29, 2026 Model glossary run 06 - Stem axis classification and combinability
Run 06 of the model-ID glossary analysis - classifies stems into the three orthogonal axes (numeric encoding, runtime, build-time technique) and tabulates which combinations stack, warn, or are mutually exclusive.
ai llm quantization
Jun 29, 2026 Model glossary run 05 - Performance & combination research notes
Run 05 of the model-ID glossary analysis - verified findings and source links on the GGUF quant ladder, MLX vs llama.cpp, NVFP4/MXFP4/FP8, QAT, TTFT vs TPS, and orthogonal build-time techniques.
ai llm quantization
Jun 29, 2026 Model glossary run 04 - Codename context resolution
Run 04 of the model-ID glossary analysis - resolves context for obscure codename tokens (rnj, hy3, jt, rsnsft, laguna, ling, etc.) by matching them against identifier strings across all three datasets.
ai llm reference
Jun 29, 2026 Model glossary run 03 - Advanced quant/format/training stems
Run 03 of the model-ID glossary analysis - lists Ollama tags carrying advanced quantization, format, and training stems (NVFP4, MXFP8, FP8, QAT, MTP, MLX, INT4, INT8).
ai llm reference
Jun 29, 2026 Model glossary run 02 - Unified stem frequency table
Run 02 of the model-ID glossary analysis - tokenizes every identifier across all three datasets and produces a unified stem frequency table, including special architectural tokens.
ai llm reference
Jun 29, 2026 Model glossary run 01 - Core ID inventory
Run 01 of the model-ID glossary analysis - extracts and counts identifier strings, families, quantization labels, variants, parameter sizes, and providers across the Ollama, OpenRouter, and Artificial Analysis datasets.
ai llm reference
Jun 29, 2026 Model-ID glossary research notes
Verified findings and source URLs collected as encountered during research for the model-ID glossary - covering GGUF quantization, NVFP4/MX formats, MLX, QAT, MTP, MoE notation, YaRN, distillation, MatFormer, DPO, LASER, reasoning models...
ai llm reference
Jun 29, 2026 Model-ID stem analysis - quality / speed / size rankings and combinability
Analysis of the architectural and quantization stems in model identifiers, ranking them on quality, speed (TTFT and TPS), and size across Mac, Linux, and WSL2 - plus a combination matrix of what stacks and what is mutually exclusive.
ai llm quantization
Jun 29, 2026 Model analysis summary
A deep dive into the different parts of the model ids - parameters, quantization, but also architectural stems like MXFP8, NVFP4, MLX, etc. - what they mean and how they interact with each other. Semi-raw analysis from claude code.
ai llm quantization
Jun 21, 2026 Reposting - trust vs provenance
Reposting a repost from a more credible source adds weight to inner post
ai provenance credibility trust
Jun 21, 2026 AI learning resources
My current recommendations for learning modern AI - changes over time
ai learning curriculum
Jun 20, 2026 OMG 🤯
Nowadays, several things are mindblowing when encountered. This post captures such things as I see them.
omg mindblown til
Jun 19, 2026 My AI stack
AI keeps changing, and the best model, agent, tool, etc. are ever changing - this post retains my current AI and software toolchain, with a log of updates to it over time.
ai updates
Jun 13, 2026 How to transfer keyboard control back from screenshare window to host on Mac
Screenshare windows take over key control in mac. Transfer to host with Ctrl-F3
howto til mac keyboardonly
May 14, 2026 Framework
Proving the seemingly obvious notion that the optimum for a human in society is to create maximum value for oneself in exchange for providing maximum value to other humans.
philosophy framework
May 13, 2026 X threads
Launches, viewpoints, and technical threads. Originals live on X; this page collects the ones worth keeping.
x threads
May 13, 2026 Reading list
A sample of reading I have found interesting
reading books papers
May 13, 2026 Products
20 years of building. Each product is part of a larger thread - making complex technology accessible and enabling people to learn, create, and discover.
products
May 13, 2026 About
Background, career, education, technical stack, design principles, and where to find me.
about
May 1, 2026 Tools
Daily-driver software and AI tools.
tools
May 1, 2026 Now
Current focus, learning, and leisure.
now
May 1, 2026 Interests
Topics I've liked over the years.
interests

Elsewhere

May 2026How to use AI effectively - the missing manualX
Jan 2026The Best Harness Beats the Best ModelX
Jan 2026Can we trust Claude Code even more?X
Jan 2026Show HN: Visualize full Claude Code CLI sessions in a rich UIHN
Dec 2025Building ahai - what, how, whyX
Dec 2025Show HN: ahai - find your ideas scattered across filesHN
Nov 2025My AI coding mindsetX
Nov 2025IRS deploys AI agentsX
Jul 2025The LLM ParadoxX
Jun 2025LLM Filter BubbleX
Mar 2025My Goto Web Chat AI AgentsBear
Mar 2025An Ode to Claude in CursorBear
Mar 2025A Cheap Way to Compare LLM KnowledgeBear
Mar 2025Long Conversations with LLMs via Language-as-CodeBear
Feb 2025List of Web Chat AI ModelsHashnode
Jan 2025A Penny for DeepSeek-R1's ThoughtsHashnode
Jan 2025Evaluating Local Models with Custom DatasetsHashnode
Jan 2025DeepSeek-R1 Thinks in CursorHashnode
Jan 2025AI DisruptorsHashnode
Jan 2025Evaluating Software by its ConfigMedium
Dec 2024State of AI End of 2024: A Brain DumpHashnode
Sep 2024Rethinking Structured Data in a World with AIMedium
Sep 2024Switch to ChatGPT o1Medium
Sep 2024Using Chat AIMedium
Sep 2024Fallacy of Shared IdentitiesMedium
Sep 2024Key Components of My AI and Technology StackHashnode
Aug 2024What Could Reduce Current AI Demand for GPUsHashnode
Jul 2024AI Assisted Software DevelopmentHashnode
Jun 2024Managing AI AnxietyHashnode

Articles on X Hashnode Medium Bear Blog Blogger Hacker News Quora (1M+ views)

Public tools & gists

2026LLM & Agentic Apps
Curated list of LLM and agentic applications across categories.Reference
2025JSON Viewer
Standalone HTML to view, navigate, and search any JSON file.Tool
2025CSV Viewer
Standalone HTML to view local CSVs in a table with sort and filter.Tool
2026Report Viewer
Asta report viewer for structured reports.Tool
2026Markdown Dark Theme CSS
Clean dark theme CSS for rendering markdown content.CSS
2025Cursor Terminal Shortcut
Workaround for Cursor IDE hijacking Cmd-K - clear terminal with custom shortcut.Tip

170+ repos on GitHub (mostly private during active development).