Tag: topic/large-language-models

Sep 23, 2026

Q: Multi-armed and contextual bandits, Bayesian optimisation, sequential Bayesian experimental design / deep adaptive design, dynamic treatment regimes with Q- and A-learning, switchback experiments and RLHF all choose actions from accumulating data. Laid out on one map, what is each optimizing, what is the state, and what feedback does it assume?

Sep 23, 2026

Q: In-context learning has been read as amortized (implicit) Bayesian inference. How does that reading compare with neural posterior estimation, variational autoencoders' amortized encoders, deep adaptive design and hierarchical models — and where does the analogy break?

Sep 23, 2026

Q: When can LLM 'silicon samples' stand in for consumer data or hand-written decision rules in an agent-based model, and what validation protocol is needed?

Sep 23, 2026

Generative Agents Architecture - Memory, Reflection and Planning

Sep 23, 2026

Validity, Bias and Calibration of LLM-Simulated Populations

Sep 23, 2026

LLM-Powered Agents - Index

Sep 23, 2026

LLM Expert Elicitation for Bayesian Networks

Sep 23, 2026

LLM-BN Decision Support Application

Sep 23, 2026

Shaposhnyk 2025 - Overview

Sep 23, 2026

Chain-of-Thought Prompting

Sep 23, 2026

Evaluating LLM Systems - Benchmarks, Hallucination and Human Preference

Sep 23, 2026

LLM Reasoning, Retrieval and Agents - Overview

Sep 23, 2026

RLHF and Instruction Tuning

Sep 23, 2026

ReAct - Reasoning and Acting Agents

Sep 23, 2026

Retrieval-Augmented Generation (RAG)

Sep 23, 2026

Reward Modeling from Human Preferences

Sep 23, 2026

Tool Use and the Agent Loop

Sep 23, 2026

LLM Reasoning, Retrieval and Agents - Index

Sep 23, 2026

Transformers and LLM Foundations - Index

Sep 18, 2026

Q: Chinchilla compute-optimal training, optimal media mix under saturating response (ROAS / mROAS, Dorfman–Steiner), and power analysis / experimental design are all budget-allocation problems under diminishing returns. What transfers between them, and what does not?

Sep 18, 2026

Homo Silicus - LLMs as Simulated Economic Agents

Sep 18, 2026

LLM Agents vs Rule-Based Agents in ABM

Sep 18, 2026

LLM-Powered Agents - Overview

Sep 18, 2026

Opinion Alignment Metrics for Language Models

Sep 18, 2026

Persona Mixture Calibration of LLM Agents

Sep 18, 2026

Silicon Samples and Algorithmic Fidelity

Sep 18, 2026

Autoregressive Language Modeling and Pretraining

Sep 18, 2026

Compute-Optimal Training (Chinchilla)

Sep 18, 2026

In-Context Learning and Few-Shot Prompting

Sep 18, 2026

Neural Scaling Laws

Sep 18, 2026

Transformers and LLM Foundations - Overview

Sep 18, 2026

Code Prompts for Causal Structure: Encoding Causal Graphs with Conditional Statements

Sep 18, 2026

Fine-tuning on Conditional Statements: Improving LLM Causal Reasoning via Code Training

Sep 18, 2026

LLM Causal Reasoning Tasks: Abductive NLG and Counterfactual Reasoning

Apr 11, 2026

Code Prompt Aspects Analysis: What Makes Code Prompts Effective for Causal Reasoning

Apr 11, 2026

Code vs Text Prompt Evaluation: LLM Causal Reasoning Benchmarks

Apr 11, 2026

Second Brain

Explorer

Tag: topic/large-language-models

Q: In-context learning has been read as amortized (implicit) Bayesian inference. How does that reading compare with neural posterior estimation, variational autoencoders' amortized encoders, deep adaptive design and hierarchical models — and where does the analogy break?

Q: When can LLM 'silicon samples' stand in for consumer data or hand-written decision rules in an agent-based model, and what validation protocol is needed?

Generative Agents Architecture - Memory, Reflection and Planning

Validity, Bias and Calibration of LLM-Simulated Populations

LLM-Powered Agents - Index

LLM Expert Elicitation for Bayesian Networks

LLM-BN Decision Support Application

Shaposhnyk 2025 - Overview

Chain-of-Thought Prompting

Evaluating LLM Systems - Benchmarks, Hallucination and Human Preference

LLM Reasoning, Retrieval and Agents - Overview

RLHF and Instruction Tuning

ReAct - Reasoning and Acting Agents

Retrieval-Augmented Generation (RAG)

Reward Modeling from Human Preferences

Tool Use and the Agent Loop

LLM Reasoning, Retrieval and Agents - Index

Transformers and LLM Foundations - Index

Q: Chinchilla compute-optimal training, optimal media mix under saturating response (ROAS / mROAS, Dorfman–Steiner), and power analysis / experimental design are all budget-allocation problems under diminishing returns. What transfers between them, and what does not?

Homo Silicus - LLMs as Simulated Economic Agents

LLM Agents vs Rule-Based Agents in ABM

LLM-Powered Agents - Overview

Opinion Alignment Metrics for Language Models

Persona Mixture Calibration of LLM Agents

Silicon Samples and Algorithmic Fidelity

Autoregressive Language Modeling and Pretraining

Compute-Optimal Training (Chinchilla)

In-Context Learning and Few-Shot Prompting

Neural Scaling Laws

Transformers and LLM Foundations - Overview

Code Prompts for Causal Structure: Encoding Causal Graphs with Conditional Statements

Fine-tuning on Conditional Statements: Improving LLM Causal Reasoning via Code Training

LLM Causal Reasoning Tasks: Abductive NLG and Counterfactual Reasoning

Code Prompt Aspects Analysis: What Makes Code Prompts Effective for Causal Reasoning

Code vs Text Prompt Evaluation: LLM Causal Reasoning Benchmarks

Liu 2025 - Overview: Eliciting and Improving Causal Reasoning in LLMs with Conditional Statements