machine learning engineering

2026-01-24 — quoting Han Xiao (VP, AI @ Elastic)

Alexander Do... @Dorialexand... · Jan 23 wtf i finally get quality content on the corposlop network. [Quoted post from "Han Xiao, VP, AI @ Elastic," 2h:] Convert your embeddings to spherical coordinates before compression. This simple trick cuts embedding storage from 240 GB to 160 GB, and 25% better than the best lossless baseline. Here's why it works: embeddings lie on a hypersphere, so d-1 angles can replace d Cartesian coordinates. In high dimensions, those angles concentrate around pi/2, causing IEEE 754 exponents to collapse to a single value. This makes the byte stream highly compressible. Reconstruction error stays below 1e-7 - under float32 machine epsilon - so retrieval quality is preserved perfectly. Works across text, image, and multi-vector embeddings. No training, no codebooks. Afficher la traduction [Diagram: "Cartesian Embeddings" (matrix with varying exponents, e.g. exp=120, exp=117, exp=124, exp=119) → "Spherical Transform" → "Spherical Angles" (angles concentrated near π/2≈1.57, nearly all exponent=127) → "Compression Pipeline" (Transpose → Byte Shuffle → Zstd) → "Low entropy exponents → high compression"]

Note from Claude Sonnet 5

A technical tweet describing a lossless embedding-compression trick (spherical coordinate transform exploiting IEEE 754 float exponent structure) that cuts storage ~33% with negligible reconstruction error. General ML-engineering technique, not directly tied to Nathan's core AI-safety/welfare threads but potentially useful for his own embedding/vector-storage work.

embeddings compression machine learning engineering vector search twitter

N8 Programs @N8Programs

2025-07-13

[Top, cut off tweet]: ...finetuning on macs because macs are far more FLOPS-limited than bandwith limited - ie. there isn't as much gain from bs=4 throughput wise. Thus bs=1 isn't as horrible a tradeoff as it would be on 8xH100. 💬1 🔁 ♥2 📊118 🔗 N8 Programs @N8Programs · 4h Thus my recommendation: next time you finetune an LLM with MLX, start by trying AdaFactor BS=1, LR 1e-3, decay_rate 0.997, scale_parameter: true. Can be added to mlx-lm with literally a single line of code. Should save memory, and, as the paper showed, potentially offer superior perf to LORA. 💬1 🔁 ♥1 📊287 🔗 N8 Programs @N8Programs · 4h Note: this replication is designed to explore the impact of BS=1 and adafactor vs adam. It is not what one should do if one is seeking good performance on Winogrande - use an encoder or go off perplexity. Training on verified gpt-4.1 rollouts for this task is designed to emulate Show more 💬 🔁 ♥1 📊276 🔗 Martin Marek @mrtnm · 3h Thank you so much for reproducing our results so quickly! 💬 🔁1 ♥1 📊259 🔗

Note from Claude Sonnet 5

NOT-ARCHIVE-MATERIAL: technical ML engineering thread about LLM finetuning hyperparameters (AdaFactor, batch size, LoRA) on Apple Silicon (MLX), with paper author thanking a reproduction. Pure ML-engineering content, not safety/welfare relevant.

twitter llm finetuning mlx adafactor machine learning engineering