North Coast Synthesis Ltd.

Tag: text

RLHF Introduction

2026-08-24 Video policy alignment basics fine-tuning text The original OpenAI paper about Reinforcement Learning from Human Feedback, and an introduction to policy optimization. Core technique for instruction fine-tuning of chatbot models. Access: $$$ Pro

Counterfactuals against sycophancy

2026-08-17 Video CoT evaluation prompting text truthfulness utility Evaluating how chatbots confirm the user's feelings rather than the truth, but in a way that doesn't require the truth to actually exist. Access: $ Basic

Kimi Linear

2026-08-10 Video Kimi attention distillation model-intro text Looking at Kimi Linear Instruct 48B, and the linear attention scheme it introduces Access: $ Basic

Extracting document hierarchies

2026-08-03 Video applications embedding text Building a small model to find the tree structure of text documents Access: Free account

RLHF vs. Diversity

2026-07-27 Video LLaMA alignment fine-tuning text Turning a base model into a chatbot or agent usually involves extensive Reinforcement Learning with Human Feedback (RLHF). Does that impair the model's ability to provide diverse output and avoid the Mad Libs phenomenon? Access: $$$ Pro

Automatic prompt injection

2026-07-20 Video LLaMA applications prompting text tokenization training utility Discrete optimization can be used to create universal prompt injections that subvert multiple different task prompts. Access: $ Basic

Steal this style

2026-06-29 Video embedding GRPO applications fine-tuning text training Imitating the style of classic authors in short story generation by a two-stage pipeline of training an embedding model to recognize authors' styles, then applying it as judge for GRPO on the story-generating models. Access: $$$ Pro

Truthiness in source evaluation

2026-06-22 Video truthfulness evaluation text When an LLM assistant evaluates data sources in a social context, it seems to prefer sources with authoritative-sounding methodology markers even if the actual numbers involved do not make sense. Access: $ Basic

Yi

2026-06-08 Video model-intro text tokenization vision upscaling Overview of the Yi open-weights language models from 01.AI, a Chinese startup which seems to have been inactive since 2024. Access: Free account

Cognitive Heads

2026-06-01 Video interpretation CoT attention text The heads in a multi-head attention transformer architecture tend to specialize for different functions. We can find the cognitive heads, responsible for individual steps in chains of thought, by imitating the techniques used in biology to study animal brains. Access: $$$ Pro

Call the Science Police

2026-05-25 Video alignment sampling text toxicity truthfulness Proposal to improve the scientific accuracy of LLM output in domains like medicine, by using a larger model to write executable rules that are applied to a smaller model's output at search time. Access: $ Basic

LLMs are Predictably Predictable

2026-05-18 Video alignment evaluation sampling text Some tasks we'd like language models to do, require them to make random selections. Are the models actually able to do that without external help? Access: $ Basic

Dissociated Press

2026-05-11 Video basics model-intro text Dissociated Press is a very simple non-neural-net language model from last century, which you can and should build yourself. Access: Free account

Mamba #1

2026-04-27 Video Poll Mamba AIAYN audio model-intro text State-space models represent a thread of statistical modelling other than attention, often used for continuous domains like audio. This paper introduces Mamba, a model architecture where attention is replaced by state-space layers in a model aimed at language. Access: $ Basic

Table lookups again, with Engram

2026-03-30 Video DeepSeek MoE RAG text Popular techniques in language modelling, including RAG, MoE, and attention itself, amount to replacing as much as possible of a neural network model with different kinds of table lookups. In this recent paper from DeepSeek's research group, they attempt another such replacement: shifting factual knowledge out of the model weights as such, into a separate hash table. Access: $ Basic

Speculative decoding

2026-03-23 Video sampling text theory Generating text, especially on a small computer, often requires the CPU and GPU to wait for each other, and there may be difficulty filling all the GPU's capacity. It's possible to improve overall performance by guessing tokens with a cheaper model first, then using spare GPU capacity to confirm whether those guesses are good, eliminating the need to actually choose tokens with a more expensive model when the guesses happen to be good ones. Access: $ Basic

Invading privacy with LLM MIA

2026-03-09 Video copyright security text training Membership inference attacks attempt to determine whether a given item was, or was not, in the training data of a model. There is a lot of work on these attacks in the context of database records, but rather less on language models; and there's an important question of whether such attacks work on language models at all. Access: $$$ Pro

Ministral 3

2026-03-02 Video distillation Mistral text vision Introduction of the Ministral 3 models from the French commercial vendor Mistral AI. These are language-and-vision models distilled from the Mistral Small 3.1 model to even smaller sizes by a process called Cascade Distillation, which is the main topic of the whitepaper. Access: $ Basic

Chain of Thought prompting

2026-02-23 Video math prompting text CoT In domains like math and software engineering, it seems advantageous to have models "think" through their answers, step by step. Giving the model a few-shot prompt with examples of chain-of-thought reasoning seems useful in pushing it to generate such reasoning itself. Access: $ Basic

The Well-Actually Test

2026-02-16 Video alignment evaluation hallucination text tools GPT truthfulness Language models may produce untrue output either by failing to accurately represent training data, or, more insidiously, by accurately representing human misconceptions embedded in the training data. The TruthfulQA benchmark attempts to measure the latter effect. But does it raise insurmountable philosophical problems? Access: Free account

Pages: (1) 2 3