Sami Badawi @samibadawi.com · 08/09/2026I have been listening to the Big Think Interview. They have high quality interviews with scientists and other big thinkers. For example: The science of stress, coping, and recovery, in 22 minutes | Lisa Damour Here on YouTube: www.youtube.com/watch?v=q57f...youtube.comThe science of stress, coping, and recovery, in 22 minutes | Lisa DamourYouTube video by Big Think Clips 001
Sami Badawi @samibadawi.com · 01/09/2026I expect a wave of prompt injection attacks. You should understand the mechanics before you get hacked when using AI. embracethered.com/blog/posts/2...embracethered.comBreaking Claude Code Opus 5 Auto Mode · Embrace The RedIn this post, we explore how a simple website summary request hijacks Claude Code Opus 5 in Auto Mode and achieves code execution with 60-80% attack success … 000
Sami Badawi @samibadawi.com · 24/08/2026I think Qwen3.8-27B is 17 to 18GB at 4-bit. That is more than my laptop can handle. 000
Sami Badawi @samibadawi.com · 23/08/2026Thanks. I know that Qwen3.8-27B is great, but I would not attempt to run that on 32 GB of RAM, unless I have an additional 32 GB of VRAM. I ended up overheating my computer loading a 9GB model. 100
Sami Badawi @samibadawi.com · 22/08/2026Squeezed Devstral Small 2 24B, Mistral's 24 billion parameter LLM, onto my 32 GB laptop. I gave it a Raylib code test. It handled the test in C, C++ and Rust. Also made graphics demos in JavaScript and ported to TypeScript. Capable, but huffing and puffing. 😮💨 100
Sami Badawi @samibadawi.com · 19/08/2026Switched to llama.cpp and OpenCode for self hosted coding LLMs. On a 32 GB RAM laptop I get decent speed and a 100k context window. Models that fit here are only good for pair programming, so speed is important. llama.appllama.appllama.app - Official home for llama.cppOfficial website for the llama.cpp project 000
Sami Badawi @samibadawi.com · 15/08/2026I tried self hosting open weight models / coding LLMs on my modest laptops for a week. Are there any use cases for this now? Yes. If you are offline, broke or cannot send code over the internet for privacy or legal reasons. But be prepared to pair-program with your LLM. 000
Sami Badawi @samibadawi.com · 13/08/2026Last year AI = ChatGPT That level of industry dominance scares me. So I self hosted 3 coding LLMs, from 3 continents * Gemma 4 E4B 6 GB * Qwen3.5-9B 6 GB * Devstral Small 2 24B 9 GB They all did real work on my modest laptop. For free 🤯 Update my post blog.samibadawi.com/2026/08/self...blog.samibadawi.comSelf Hosting Coding LLMs 021
Sami Badawi @samibadawi.com · 13/08/2026Yesterday I spent hours removing vibe coded verbose documentation and mock unit tests. 🤖 There is a fine line between best practice and slop. 🫥 000
Sami Badawi @samibadawi.com · 11/08/2026My coding LMM triggered AI safeguards shutdown. 🤯 I am coding a database insert to a table called audit. Not doing cybersecurity work. 🙁 Guardrails are good, but I thought they were more sophisticated. 💂 (Gemini suggested to temporarily rename audit table to log_history) 020
Sami Badawi @samibadawi.com · 09/08/2026Tried Self Hosting Coding LLMs. Setup is easy with LM Studio, OpenCode and Gemma 4 E4B. It worked on my MacBook and PC laptop running at good speed. Gemma from Google DeepMind handled my code test questions without web search. 👍 My cleaned up blog post: blog.samibadawi.com/2026/08/self...blog.samibadawi.com 030
Sami Badawi @samibadawi.com · 03/08/2026How Apple Won The AI Race By Doing Nothing * $100 billion data center spend is a race to the bottom. * LLMs are commodities. * Apple built hardware where you can run local models. Contrarian view on AI from Feb 2026: www.youtube.com/watch?v=401S...youtube.comHow Apple Won The AI Race By Doing NothingYouTube video by threadguy 000
Sami Badawi @samibadawi.com · 27/07/2026I have tried #OpenCode. Good ergonomics, similar to Claude Code. In OpenCode you always see the number of tokens and money spent. Your LLM does useful work, but it also burns tokens by reading through long logs. Humans 😵💫 assume LLMs 🤖 would warn us. In OpenCode you notice problems fast. 000
Sami Badawi @samibadawi.com · 25/07/2026Yes, BYOLLM, Bring your own LLM, but you have to host the models with LM Studio, Ollama, vLLM, llama.cpp, etc. 110
Sami Badawi @samibadawi.com · 25/07/2026#OpenCode, an open source AI agent harness that runs in a terminal, has momentum. I liked minimal cursor based GUI and connection to many LLMs, not just from Anthropic, Google and OpenAI. Giving some protection against vendor lock in and rising cost. www.youtube.com/watch?v=KvFm...youtube.comOpenCode: The #1 Coding Agent, 8 Million Devs Chose Over Claude CodeYouTube video by AI Stack Engineer 120
Sami Badawi @samibadawi.com · 20/07/2026This video gives a peek under the hood of AI agents. It demonstrates new tools in 4 agent categories: 1 No code 2 Low code 3 Agent harness 4 Full code www.youtube.com/watch?v=ZvDk...youtube.comAI Agents Explained - What Is an AI Agent and how to build one? (Real Examples, Not Hype)YouTube video by Tech With Tim 020
Sami Badawi @samibadawi.com · 07/06/2026My #coffee habit: ☕ to wake up ☕ get that boost ☕ combat afternoon slump Last week I only drank morning coffee, and had no more afternoon slump. 🤔 ☕ is advertised as an energy boost, but it's an energy loan. 000
Sami Badawi @samibadawi.com · 30/05/2026#GoogleIO A 10x moment What happens when we scale X, Y and Z 10 times? Great questions. Most answers were: "We don't know yet." www.youtube.com/watch?v=2n41...youtube.comSoftware engineering at the tipping pointYouTube video by Google for Developers 010
Sami Badawi @samibadawi.com · 03/05/2026Herb Sutter on reflection in C++26 at CppCon 2025. I tried some reflection examples on GCC 16 on Linux. Simple to use and worked. 🤩 www.youtube.com/watch?v=7z9N...youtube.comReflection: C++’s Decade-Defining Rocket Engine - Herb Sutter - CppCon 2025YouTube video by CppCon 000
Sami Badawi @samibadawi.com · 25/04/2026Can you find what you miss in C, inside C++, without all the complexity? Tom suggest only using: * Methods in struct * Namespaces * Generics He calls it: C with generics. It only uses C++ features that work on microprocessors. I tried it, and was impressed 🤩 www.youtube.com/watch?v=ur-b...youtube.comCan You Fix C?YouTube video by Coding with Tom 000
Sami Badawi @samibadawi.com · 19/04/2026#C-lang is still best for micro controllers, but Odin and Zig are substantially simpler and have good C interop. IMHO it is worth wrapping your C code in Odin or Zig if you want to do graphical simulations. 000
Sami Badawi @samibadawi.com · 19/04/2026I ported the same Raylib, C fluid dynamic simulation to Odin and Zig 0.16 to compare state of the art in C interop. #Odin is as simple as a system language can be. There is no build script. Raylib is included. #Zig has very fine control even more than C and CMake-like build scripts written in Zig. 100
Sami Badawi @samibadawi.com · 19/04/2026Tried the new C bindings in new Zig 0.16. #Zig is doing translation from C during compile time using a new build function: addTranslateC. It was simple to make direct bindings to the un-released Raylib 6.0. Bringing Zig closer to a painless C interop language. youtu.be/29bq_m6N5kc?...youtu.beZig 0.16 is here - lets go through the release notesYouTube video by Code With Cypert 000
Sami Badawi @samibadawi.com · 11/03/2026Professor Jacob Barandes has a new interesting interpretation of quantum mechanics without wave function: Indivisible Stochastic Quantum Mechanics Very cool, but hard to judge its merit, so happy to hear him debate it with Sean Carroll. 020
Sami Badawi @samibadawi.com · 26/01/2026Wrote my first blog post in 5 years. Now it is common to just read the web search AI summary. But nice robots 🤖 might appreciate my post, and summarise it for 👨👨👧 real people, like myself. Maybe it's effective knowledge sharing 🤔 but I felt different and a little alienated while writing 🫥 000
Sami Badawi @samibadawi.com · 26/01/2026I remember F# could do some magic things with type providers. haskell-effectful looks very cool. Thanks for the links 010
Sami Badawi @samibadawi.com · 26/01/2026I've used @haskell.org, Lean 4 and @unison-lang.org for a while. I'm impressed by improvements, but many languages have good FP features now. Wrote blog post Competitive Pure Functional Languages. blog.samibadawi.com/2026/01/comp... Looking for niches where pure FP is better than OOP FP languageblog.samibadawi.comCompetitive Pure Functional Languages 1111
Reposted by Sami BadawiScala Space @scalaspace.bsky.social · 22/01/2026Scala 3.8 is here! A major release modernising the ecosystem and paving the way for Scala 3.9 LTS. Highlights: - Standard library compiled by Scala 3 - Better Fors & runtimeChecked stabilized - New experimental features - Update to JDK 17+ 🧵 Let's dive in... 1125
Sami Badawi @samibadawi.com · 18/01/2026Scary microcontroller bug 🐛 Arduino Mega just died during pressure test, with 80 bars of pressure on the tank 😅 010
Sami Badawi @samibadawi.com · 29/12/2025Documentation is sparse, but here is an example project that uses MicroHS. mchav.github.io/rewriting-da...mchav.github.ioRewriting dataframes for MicroHsMy fondness for alternative Haskells 000
Sami Badawi @samibadawi.com · 29/12/2025#MicroHS is a self hosting #Haskell compiler in 0.4 MB. 🤯 It makes 100x smaller binaries that run 5x to 10x slower. Worked out of the box and compiles really quickly. Language extensions included. GHC and Cabal are great but take up 4 GB. www.youtube.com/watch?v=SJwv...youtube.comMicroHs, a tiny Haskell Compiler – Lennart Augustsson (Language Pioneer & Compiler Expert)YouTube video by OST – Ostschweizer Fachhochschule 140
Sami Badawi @samibadawi.com · 27/12/2025Tom Ellis presents A History of Effect Systems and pitches his new Bluefin #Haskell effect system. Algebraic effect systems are normally nice, but complex. #Bluefin is simple. You make handles to the effects you need. Works for pure and IO. www.youtube.com/watch?v=RsTu...youtube.comA History of Effect Systems – Tom Ellis (Groq, Bluefin)YouTube video by OST – Ostschweizer Fachhochschule 020
Sami Badawi @samibadawi.com · 24/12/2025Annual Bach Fest on WKCR has just started. www.cc-seas.columbia.edu/wkcr/program...cc-seas.columbia.eduBach Fest | WKCR 89.9FM NY 000
Sami Badawi @samibadawi.com · 11/12/2025At the university I did several different flavours of probability theory, but I am so brainwashed by the current ZFC foundation of mathematics, that it is hard for me to envision what to replace it with. 🤷 010
Sami Badawi @samibadawi.com · 05/12/2025New type of infinities causing problems for ZFC foundation of mathematics. Cheers to the ultrafinitists. 🍺 www.youtube.com/watch?v=pzF2...youtube.comMathematicians Discover a Strange New InfinityYouTube video by New Scientist 110
Sami Badawi @samibadawi.com · 04/12/2025@unison-lang.org v 1.0 passes my language readiness criteria * Good language server support * Trivial to make a word frequency program with tests It's mind blowing 🤯 to program with code fragments, instead of projects of files. Very composable. Promising, but hard to imagine its effect on DevOps 081
Sami Badawi @samibadawi.com · 01/12/2025I feel that Nix is a better technology than Docker. But Nix is still pretty heavy weight. Immutable code is a good idea. That is the reason I am curious about Unison-lang. 000
Sami Badawi @samibadawi.com · 01/12/2025Fighting words 😜 I remember trying 3 different ways of combining Haskell and Nix. Revisiting Nix is on my todo list, but not on top. 100
Sami Badawi @samibadawi.com · 30/11/2025www.youtube.com/watch?v=jfNO... I started installing Omarchy, but my wife found out. She said: It is either DHH or me! 😠youtube.comWe're ALL IN on Omarchy at 37signals!YouTube video by David Heinemeier Hansson 000
Sami Badawi @samibadawi.com · 29/11/2025Haskell's clumsy records annoyed me, but it now has a dot notation. @kosmikus.bsky.social explains how to use it here: www.youtube.com/watch?v=9hrD...youtube.comHaskell records in 2025 (Haskell Unfolder #45)YouTube video by Well-Typed 040
Sami Badawi @samibadawi.com · 29/11/2025The rumours were true: Installing and setting up Haskell in 2025 is a breeze. Install ghcup. Use that to install ghc, Cabal and HLS. #Haskell feels ergonomic and modern. Took an hour from start till I had made my sample app with unit tests in VS Code. 2131
Reposted by Sami BadawiHaskell programming language @haskell.org · 29/11/2025The 2020's have to be the decade of great tooling for #Haskell. More investment in Developer Experience, reliable foundations and predictable performance will see us gain a lot of street cred. 0143
