Posts

All the articles I've posted.

• I tested my Obsidian plugin by remote-controlling Obsidian on another PC

  19 Oct, 2026

  To test an Obsidian plugin in the real app before each release, I drove Obsidian on another PC over the Chrome DevTools Protocol (CDP), deploy to button clicks.

• Splitting the question into three made the Decisions API as accurate as Luna

  18 Oct, 2026

  I tuned OpenAI Decisions API and Jev prompts per their docs. Split into three true/false questions, Decisions API got 36 of 37 pairs right; trimming input hurt.

• OpenAI's Decisions API was fast, but it didn't fit my merge criteria

  17 Oct, 2026

  I compared OpenAI's Decisions API, Jev, and gpt-6-luna on merging duplicate notes. Decisions API was fastest, but confidently wrong on my multi-part rule.

• Laptop 2's OpenAI reasoning effort turned out to be Medium

  15 Oct, 2026

  The work laptop's OpenAI reasoning effort was the default Medium, confirming chunk size alone caused the LLM summary errors. The two are separate knobs.

• Raising LLM request concurrency from 2 to 4 surfaced two other bugs

  14 Oct, 2026

  Raising parallel LLM requests from 2 to 4 kept summary accuracy. The audit found missed Korean-English note merges and Korean headings on English notes instead.

• I used embedding similarity to find out why Korean and English notes wouldn't merge

  13 Oct, 2026

  Korean and English notes on one concept never merged. OpenAI embeddings put them at 0.77, below same-language duplicates; a 0.70 similarity threshold fixed it.

• OpenAI reasoning effort wasn't the culprit behind the fidelity problems

  12 Oct, 2026

  Lowering OpenAI reasoning effort from High to Medium didn't add LLM summary errors. Note count and run time changed a lot instead; chunk size governed accuracy.

• Getting ready to rerun the experiment, git conflict markers got committed as-is

  11 Oct, 2026

  Continuing a chunk-size experiment at home, alternating two laptops on one git repo committed conflict markers into 77 files. Then I suspected reasoning effort.

• Just lowering the LLM chunk size made the fidelity problems go away

  10 Oct, 2026

  I compared the same 30 sources changing only the chunk size, how many go to the LLM at once. Summary errors that drop people and quotes fell from 40% to 0%.

• 189 notes an LLM had organized became 63 one day

  9 Oct, 2026

  I had an LLM turn the same 30 sources into Obsidian notes, and just switching machines cut them from 189 to 63. Not one cause, chunk size, but two settings.