RSS Amplifier

Blog

Aniss Djellal

I primarily work on LLM fine-tuning and distillation, generating synthetic data, and creating Agents.

djellalmohamedaniss.github.ioSource feed ↗4 posts

Live Last read · last published · next check

Latest posts

Finding the number of intersections between 100 random chords on a circle

A solution for the 3blue1brown's june 2026 puzzle

Trading MatMuls for SRAM Lookups: A 3-Bit Edge Architecture

What if we could run inference with a small set of tensor cores?

An approach to calibrating LLM reasoning effort

Controlling reasoning effort in LLMs ( the gpt-oss-style ) and Calibrating LLM Reasoning effort via Label-Free Alignment.

Stop Using Embeddings for Everything in RAG

Why deterministic query translation should often come before embeddings in enterprise RAG systems, and how to combine both in a hybrid approach.