Rami's Readings #136 - Ollama & Claude Code
Welcome to Rami’s Readings #136 - a weekly digest of interesting articles, papers, videos, and X threads from my various sources across the Internet. Expect a list of reads covering AI, technology, business, culture, fashion, travel, and more. Learn about what I do at ramisayar.com/about.
👋🏼 Welcome New Subscribers
Hello! A hearty thank you for subscribing to Rami’s Readings! There are quite a few new subscribers this week, thanks to recommendations from The AI Ethics Brief, Product Byte, and The VC Corner. I am thrilled to have you on board! In this newsletter, I curate the best papers, tweets, and articles I have read during the week focusing on LLMs, AI, economics, business, and technology news. You can learn more about me on my website.
Happy New Year! We’re back to our regular publishing schedule. Catch up on yesterday’s newsletter where I shared my plans for 2026, it’s worth a quick read!
🤖 AI Reads
Ollama Launches Claude Code, Open Code, Codex & Droid Support
Notes: Ollama & LM Studio are my go-to tools for running local large language models easily. Ollama just made it easy to configure Claude Code to work against a variety of local coding models (GPT-OSS 20B, Qwen3-Coder, etc.)
Qwen3-TTS Family Open Sourced: Voice Design, Clone, and Generation
Notes: Really really really good TTS model from Alibaba.
Sopro TTS
Notes: Lighter weight TTS model with voice cloning than Qwen3-TTS (169M parameters)
Soprano: Instant, Ultra‑Realistic Text‑to‑Speech
Notes: Even lighter weight English-only TTS model, but extremely small (80M parameters).
Ministral 3 Paper
Notes: Mistral AI’s papers are always worth a read.
TranslateGemma Technical Report
Notes: Translation model from Google. Download from HuggingFace.
Demystifying Evals For AI Agents
Notes: Great introduction on evals from Anthropic. Read this first and then look at Evalry.
Evalry: Compare 300+ LLM Models on Your Use Case
Notes: Often repeated in this newsletter, benchmark models against your own use cases. Here’s a tool to help you do it.
💼 Business Reads
What Stanley Kubrick Got Right About Artificial Intelligence
Notes: Fun read!
Addy Osmani On The Next Two Years of Software Engineering
Notes: Spot on. I particularly like the recommendations for junior engineers.
Singapore Pours $786 Million Into Race to Become AI Powerhouse
Notes: Good announcement! More details here.
🔀 Other Reads
YC Startup Genealogy
Notes: Neat website!
Signing off from Redmond, WA.