Epistemic Noise

AI · Language · Uncertainty

I build systems that understand.I write about why we often don’t.

I'm Aissam Outchakoucht, an AI engineer building language, speech, and agentic systems. This is where I share things I build, ideas I'm exploring, and essays about uncertainty, perspective, intelligence, and the strange business of knowing things.

Artificial IntelligenceLanguagePerspectiveOpen SourceUncertaintyAgentsKnowledgeSpeechArtificial IntelligenceLanguagePerspectiveOpen SourceUncertaintyAgentsKnowledgeSpeech

The rooms

Four places to look

A personal site, not a brochure. Pick a room.

Work

Things that shipped

Datasets, libraries, pipelines, chatbots, and voice skills.

All projects

NLP Explained

Notes you can read in two minutes

From foundations to advanced techniques — boiled down, simplified, and packed tight.

All reads
2 min2 min

Mixed Precision vs. Quantization

Mixed precision and quantization are two techniques that can significantly reduce the memory and computational requirements of AI models.

2 min2 min

Prompt Chaining

Prompt chaining is a technique that involves combining multiple prompts to generate more complex and nuanced responses from AI models.

2 min2 min

Reinforcement Learning from Human Feedback (RLHF)

RLHF is a method that incorporates human feedback into the training process of AI models. Unlike traditional training, which relies solely on datasets and metrics, RLHF uses human evaluators to guide the model's learning.

2 min2 min

Vector Databases in NLP

Vector databases are a powerful tool for storing and querying high-dimensional vectors. They are very useful in comparison and search tasks in NLP

2 min2 min

Exploring LangChain

LangChain is a tool for building AI applications. It simplifies the process by making it easier to connect and manage the various components.

2 min2 min

The Art of Fine-Tuning

Finetuning is the magic wand that transforms a general-purpose AI model into a domain-specific maestro.

2 min2 min

How Prompt Engineering Shapes AI Interactions

Prompt engineering is the art of crafting the perfect question or instruction to elicit the desired response from an AI model.

2 min2 min

Retrieval-Augmented Generation (RAG)

RAG combines the best of both worlds: the vast knowledge of a search engine and the creative storytelling of a language model.

Approach

How I actually think

Measure the uncertainty

A lot of what people call knowledge is borrowed confidence. The useful move is to notice where the chain of justification actually stops.

Ship conversational systems

Chat, voice, agents. The interesting work is not the demo — it is the system that holds up when a real person starts talking.

Open-source Darija

Moroccan dialect is spoken by millions and still under-served in NLP. Datasets and tools should exist in the open.

Write in public

Short notes, long essays, tutorials. Writing is how the work gets inspected — by you first, then by anyone else.

8+

Years in AI

500k

DODa entries

61

2-minute notes

11

Papers

Thoughts

A little less certainty

All essays

Write / collaborate

If the question is still open, write.

Conversational AI, Darija, production NLP, or an essay that should exist.