_index.org

Living

Last edited: August 8, 2025

Something is considered “Living” when they exhibit two main biological functions

Two Main Functions of Life

theories of origin of life

  • Manfred Eigen ("RNA-World" theory): genes form, constructing enzymes, forming cells
  • Alexander Oparin: cells form, creating enzymes as needed, forming the genes to encode them
  • Freeman Dyson: Dyson’s Model of Life—basically the Oparin model, but with more specifics about how genes evolve

LLaMA

Last edited: August 8, 2025

LLM for Teacher Feedback

Last edited: August 8, 2025

Qualitative Changes in Teaching via LLMs

  • no clear sign that there are qualitative changes via GPT
  • no clear catering to students

important questions

  • how to treanslate training into practice?
  • how to cater to student needs?
  • what to do with flawed assessments?

Teacher Training

Conventional Teacher Coaching

  • not scalable, requires observation, and will give feedback
  • not data driven, not adaptive—expertise is hard

AI powered coaching

  • provide data-driven reflection opportunities
  • can be personalized
  • but not personalized with a human connection

Automated NLP Feedback

  • talk time measurements
  • reflection opportunities, NLP measurements, etc.

GPT wasn’t good at evaluating teachers

  • GPT is gaslighting the teachers—rewording the existing work, so no novelty
  • GPT is fairly faithful, the information is relevant, and

Punitive vs. Restorative Classroom Management

Classroom Management

  • reducing use of exclusionary discipline
  • improve classroom management to prevent escalation
  • teachers feel stressed + under-prepared

Examples

“sit down now” vs. “do you need a break”

LLM MPC

Last edited: August 8, 2025

model predictive control

Recall: MPC—pick some small horizon, define a cost function given the state, optimize

LLMs are fantastic search engines, so I built one

Last edited: August 8, 2025

For the past 20 years, semantic indexing sucked.

For the most part, the core offerings of search products in the last while is divided into two categories:

  1. Full-text search things (i.e. every app in the face of the planet that stores text), which for the most part use something n-grammy like Okapi BM25 to do nice fuzzy string matching
  2. Ranking/Recommendation things, who isn’t so much trying to search a database as they are trying to guess the user’s intent and recommend them things from it

And we lived in a pretty happy world in which, depending on the application, developers chose one or the other to build.