LoRA (Low-Rank Adaptation) in AI
A new section for Fine-Tuning Techniques is created to hold the LoRA document, and the LLM Architecture section is de-duplicated.
Llm
Function Calling Support in LLM Models
Explains function calling (tool use) in LLMs: how models emit structured requests to invoke external functions, the request-execute-return loop, provider support, and practical reliability notes.
What is Speculative Decoding?
Explains speculative decoding, which pairs a small draft model with a large target model to accelerate LLM inference without changing outputs.
Mixture of Experts in AI
Explains sparse Mixture-of-Experts (MoE) architecture with conditional computation, router/gate mechanisms, load balancing, and trade-offs vs. dense models.
Local + Frontier Model Collaboration Patterns in Open Source Harnesses
As local LLMs improve, harnesses are learning to pair them with frontier models. A look at the four collaboration patterns already shipping in open source.
RLVR vs. the Agent Loop: Training-Time vs. Inference-Time
Distinguishes RLVR as training-time weight updates from inference-time agent verification loops.
The Modern LLM Training Pipeline
Explains the four-stage modern LLM training pipeline from pre-training through verifiable-reward RL.
The Modern LLM Training Pipeline
Explains the four-stage modern LLM training pipeline from pre-training through verifiable-reward RL.
Jailbreaking LLMs: A Security Researcher's Field Guide
Field guide to LLM jailbreaking attack surfaces, threat modeling, defenses, and responsible disclosure.
Adaptive Thinking in Claude Models
Explains Claude adaptive thinking, effort levels, fixed-budget deprecation, and hidden reasoning display.
AdapTime: Adaptive Temporal Reasoning in LLMs
Paper summary of AdapTime, an adaptive planner for temporal reasoning in LLMs.
Agent Harness Six Components (E, T, C, S, L, V) — Survey Summary
Summarizes the six-component agent harness model: execution, tools, context, state, hooks, and evaluation.
TurboQuant
Explains TurboQuant, a rotation-based vector quantization method for KV-cache compression and vector search.
ARIS: Multi-Agent Reliability Patterns
Patterns from ARIS for reliable multi-agent research using adversarial review, audits, and persistent memory.
CompactRAG
Explains CompactRAG, a multi-hop RAG method using offline atomic QA pairs and fixed two-call inference.
Graph-based Agent Memory
Explains graph-based memory for LLM agents, including taxonomy, GAM consolidation, and hybrid retrieval.
LLM Thinking Token Budgets
Explains thinking-token budget parameters, provider naming, cost-latency tradeoffs, and completion-cap interactions.
LLM Prompt Cache Options Across Providers
Compares prompt/KV cache TTLs, controls, pricing, scope, and strategies across major LLM providers.
LLM Prompt Caching: Implicit vs Explicit
Explains implicit vs explicit LLM prompt caching, prefix constraints, provider support, and when to use each.
Why LLM Caching Is Only for Input Tokens
Explains why LLM prompt caching applies to reusable input-token prefill, not sequential output decoding.