🧠 Memory Models - nmarshall

🤖AI Coding Tools News Blog

octavio.substack.com··Substack

ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.

🔥PyTorch Code

github.com··Hacker News

Less-relevant results

What Salesforce Learned from 20,000 Enterprise Agent Deployments

🤖AI agents News Blog

blog.bytebytego.com·

ariadne: a CI/CD Optimizing Compiler

🤖Automation

abm-77.dev·

jeffhuen/RustyCSV: High-performance CSV parsing for Elixir. Rust NIF with SIMD acceleration, parallel parsing, and bounded-memory streaming. Drop-in NimbleCSV replacement.

⚡SIMD Optimization Code

github.com··Hacker News

Why the Startup That Raises the Most Money Usually Loses

🧩Low-code

siliconopera.com·

Your Lambda isn't leaking memory — your metrics are lying to you

☁️Cloud Computing Blog

engineering.taktile.com··Hacker News

defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes

🤖AI agents Code

github.com··Hacker News

We've boosted the performance of Grand Theft Auto V by 30% at night

⚙️CPU Microarchitecture Blog

danielgp.com··Hacker News

wallidsaydi-creator/hom-local: HOM Local — open-source local-first AI memory kernel

🗃️SQLite Code

github.com··Hacker News

The C++ Documentary Won't Show You a Number. I Will.

🔍Borrow Checker

hftuniversity.com··Hacker News

How to Measure Time To First Token (TTFT) in AI Systems

⚡API Performance

qainsights.com··Hacker News

No more posts from nmarshall's subscribed feeds.

Scour all 25255 feeds Learn more about Feeds

Fine-tuning vs RAG vs MeMo: Where should LLM Knowledge Live?

The ROI of AI coding looks completely different when you are a bootstrapped founder

ml-from-scratch-book/code: Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.

What Salesforce Learned from 20,000 Enterprise Agent Deployments

ariadne: a CI/CD Optimizing Compiler

jeffhuen/RustyCSV: High-performance CSV parsing for Elixir. Rust NIF with SIMD acceleration, parallel parsing, and bounded-memory streaming. Drop-in NimbleCSV replacement.

Why the Startup That Raises the Most Money Usually Loses

Your Lambda isn't leaking memory — your metrics are lying to you

defai-digital/ax-engine: Apple Silicon LLM runtime supporting Gemma 4 and Qwen 3.6 MTP modes

We've boosted the performance of Grand Theft Auto V by 30% at night

wallidsaydi-creator/hom-local: HOM Local — open-source local-first AI memory kernel

The C++ Documentary Won't Show You a Number. I Will.

How to Measure Time To First Token (TTFT) in AI Systems