Sun, May 3, 2026

Weekly Notes and Discoveries | S Anand

Always add indecisiveness, inaction, "other", "not applicable", etc. as an option to LLMs. They are trained for decisive responses and pattern matching, so we need to guide the the other way. Martin Fowler #future #llm-ops

Claude Code stores the logged in OAuth token at ~/.claude/.credentials.json. We can use that to fetch https://api.anthropic.com/api/oauth/usage and retrieve Claude usage and reset times. uvx ccusage does this automatically, but I prefer my own script.

Ontology matters in the AI era. But some stuff matters more, and some less. #code-agents
- 🟢 MORE: Definitions: what "customer" means
- 🟢 MORE: Constraints: e.g. "don't reclassify loans"
- 🟢 MORE: Interactions: how to verify, coordinate, delegate, ...
- 🔴 LESS: Creating ontologies: agents can do that.
- 🔴 LESS: Completeness and rigor: agents tolerate uncertainty.
- 🔴 LESS: Proprietary: agents can reverse-engineer.

Research: Does making an emotional decision before learning create a stronger cross-domain knowledge transfer than making a rational one? #future

"... the eigenquestion is the question where, if answered, it likely answers the subsequent questions as well." Shishir Mehrotra & Matt Hudson #future

There are several industries / markets that MBA case studies rarely cover (ChatGPT): Kirana stores; Care (child care, elder care, domestic work); Faith (finance, food, media, education); Remittances; Gambling (lottery, sports betting, gacha); Scams & organized fraud; Counterfeiting; ... #business #future