Tag: llm-concepts
All the articles with the tag "llm-concepts".
-
llm-concepts7 min readHallucinations and Jailbreaks: The Two Ways LLMs Fail
LLMs produce confident wrong answers and can be tricked into ignoring safety rules. What is actually happening and why both failures are hard to fix.
-
llm-concepts8 min readThe 2026 Model Lineup: Who Ships What
A field guide to the 2026 frontier and open-weight model field, and a practical way to think about which model to actually pick.
-
llm-concepts7 min readMultimodality: Teaching Models to See and Hear
A multimodal model is not many models in a trench coat. It is one transformer trained to treat pixels, audio, and text as the same kind of thing.
-
llm-concepts7 min readReasoning Models: Chain-of-Thought and Test-Time Compute
Reasoning models do not have a new architecture. They have a new training recipe and permission to think for longer before answering.
-
llm-concepts7 min readModern Alignment: RLHF, DPO, and Constitutional AI
A base model just predicts tokens. Alignment turns it into an assistant that follows instructions and refuses harmful ones.
-
llm-concepts8 min readMixture of Experts: Why 671B Does Not Equal 671B
A 671B Mixture of Experts model can be faster and cheaper to run than a dense 70B. The headline parameter count stopped meaning what it used to mean.
-
llm-concepts6 min readParameter Counts and Scaling Laws: What 70B Actually Means
What does 70B actually mean? It tells you about memory requirements, inference speed, and training costs, but almost nothing about model quality on its own.
-
ai8 min readContext Windows: Why Your AI Has a Working Memory Limit
Context windows are not memory. They are working memory. Here is what the model can see right now, why extending that limit is hard, and what it costs to try.
-
ai9 min readPositional Encoding and Sampling: How the Transformer Finds Position and Picks Its Next Word
Attention cannot tell 'the dog bit the man' from 'the man bit the dog.' Positional encoding fixes that. Then sampling decides what word the model actually says.