Monthly Archives: June 2025

Capo Noli

2025 Reading list (updated as we go)

Carbon : a successor language for C++ https://github.com/carbon-language/carbon-lang

Decentralize : https://decodeproject.eu/ ( https://dcentproject.eu/ )

Hardware memory models : https://research.swtch.com/hwmm

Who remembers UUCP ? NNCP : https://salsa.debian.org/jgoerzen/docker-nncpnet-mailnode/-/wikis/home

ProtectEU: A European Internal Security Strategy https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=celex:52025PC0148

Gödel’s theorem debunks the most important AI myth. AI will not be conscious | Roger Penrose (Nobel) https://www.youtube.com/watch?v=biUfMZ2dts8

Prompting AIs Will Turn Us into “Benevolent Dictators” ? https://paulborile.medium.com/prompting-ais-will-turn-us-into-benevolent-dictators-7a1ba270c0b2

Tuning go for ms to μs performance : https://renaldid.medium.com/from-milliseconds-to-microseconds-tuning-go-for-extreme-performance-6b1ce871f98f

Interesting analogy : https://intenseminimalism.com/2025/learning-and-leveraging-ai-as-interaction-material-in-your-product/

Lost in Linux kernel tuning ? explore all sysctl settings https://sysctl-explorer.net/

The term for this style of on-command software development is “vibe coding” — Andrej Karpathy, cofounder of OpenAI, coined it last month and it instantly caught on. The idea: Instead of developers writing literal lines of code, anyone can direct AI to build based on a prompt… and tweak from there. In Kaprathy’s words: “it’s not really coding — I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.”
https://blog.medium.com/a-definition-of-vibe-coding-or-how-ai-is-turning-everyone-into-a-software-developer-07346324b826

EuroStack – A European Alternative for Digital Sovereignty https://www.euro-stackreport.info/

Biggest sponsor of Go language is … Microsoft 🙂 https://devblogs.microsoft.com/typescript/typescript-native-port/

Porting Linux to Apple Silicon  https://asahilinux.org/

Platform-independent low-level JIT compiler : https://github.com/zherczeg/sljit

Apollo mission audio/images in realtime (obviously we have never been to the moon, they did all this with photoshop in the 70s 🙂 ) https://apolloinrealtime.org/

Permacomputing : https://permacomputing.net/concepts/ get the idea

We are (Are we) destroying software (?) https://antirez.com/news/145

Relive the Apollo missions in realtime : https://apolloinrealtime.org/

The study that changed everything in ai/llm : google brain 2017 https://arxiv.org/abs/1706.03762v1

Exit cloud for a big service : https://world.hey.com/dhh/the-big-cloud-exit-faq-20274010

Earth-Sun Lagrange L2 point is getting crowded : gaia, euclid, webb and next one is https://en.wikipedia.org/wiki/Nancy_Grace_Roman_Space_Telescope

Testing non deterministic systems : https://medium.com/@sermineldek/testing-non-deterministic-behaviors-in-ai-systems-challenges-and-innovations-6e1996025504

Emissions fell by 4% in Q1 and 2.6% in Q2, while GDP grew by 0.3% and 1%, respectively, compared to the same quarters in 2023, according to the latest statistics. This demonstrates that climate action and economic growth can go hand in hand : https://ec.europa.eu/eurostat/en/web/products-eurostat-news/w/ddn-20241115-2

Milano

June 2025 : current AI Agent frameworks

Just a recap for my personal use

  • LangChain: The oldest and most comprehensive framework, offering extensive integrations but often criticized for its steep learning curve and boilerplate code.
  • LlamaIndex: Primarily focused on data-intensive applications, excelling at connecting language models to external data sources through advanced retrieval and indexing.
  • AutoGen (Microsoft): A multi-agent framework that shines at creating conversational agents that can collaborate and delegate tasks to solve complex problems.
  • CrewAI: Designed for orchestrating role-playing autonomous agents, making it easy to define agents with specific jobs and have them work together in a structured crew.
  • AgentVerse: A versatile framework that provides a “lego-like” approach to building and composing customized multi-agent environments for various applications.
  • ChatDev: A “virtual software company” framework where different agents (CEO, programmer, tester) simulate a software development lifecycle to complete coding tasks.
  • SuperAGI: A developer-centric framework focused on building autonomous agents with useful features like provisioning, deployment, and a graphical user interface.
  • AI Droid (by Vicuna): A lightweight and fast framework designed for mobile and edge devices, prioritizing efficiency and low-resource consumption.
  • GPTeam: Similar to ChatDev, this framework uses role-playing agents (like product managers and engineers) to collaboratively work on development tasks from a single prompt.
  • Agenta: An open-source platform that helps developers evaluate, test, and deploy language model applications with features for prompt management and A/B testing.
  • OpenAI Assistants API: OpenAI’s native solution for building stateful, assistant-like agents directly on their platform, handling conversation history and tool integration internally.
  • LangGraph: Built on LangChain, this framework is specifically for creating cyclical, stateful multi-agent workflows, treating agent interactions as steps in a graph.