Mitja Martini

When I was young, I thought of senior engineers, consultants, etc. as experts that are more effective.

Today I learned about Rashid’s solution to export ChatGPT conversations to Markdown or even PDF if you like.

The recent RAM price hikes have pushed GPU prices up as well.

Christian Posta from Solo.io has written an interesting Deep Dive into MCP and A2A Attack Vectors for AI Agents.

In case you haven’t tried vibe coding, recently, you should probably try it (again).

Here’s a trick from the 80s that’s still useful, today: Van Halen’s live shows were potentially dangerous.

So far, my web apps run on a Dokku server.

Vibe scripting, for me, is when I develop small tools for myself with the help of coding agents.

Terms and conditions

OpenAI just releasesd MCP connectors and ChatGPT developer mode beta.

Development Containers or just “devcontainers” add a layer of security, simplify developer onboarding enables developing in parallel with isolated environments.

I’ll help you turn prompts into reliable AI features and apps.

Privacy statement

About me

In this article, I document some non-technical things I’ve learned migrating my blog from Jekyll to Hugo.

Notes of a whirlwind intro to evals for voice agents by Kwindla and swyx

After reading a nice post via HN about On Stepping Back, I habitually scrolled through the comments and found this nugget by evrimoztamur: Interacting with LLM coding tools is much like playing a slot machine, it grabs and chokeholds your gambling instinc…

Pipecat Cloud is located in the US.

A somewhat hidden feature of Ollama is K/V Cache quantization.

Here are my notes on the session about deploying voice agents to production which is part of the Voice Agents Course.

In The Batch 300, Andrew Ng shared some insights about the importance of speed for startups and how to move fast as a startup.

I’m so happy to be part of the Voice Agents Course by Kwindla and swyx.

How to Install Docker and Docker Compose on Raspberry Pi OS (rootful and rootless).

AI Apps are often expected to be realtime.

A look at the NVIDIA RTX 5090 specs for local LLM inference.

The ChatGPT search feature can also search and use information from intranet websites.

An interesting statement by Yann LeCun.

A quick tip to make working a bit easier.

This article describes how to deploy a static site on Dokku, including activating Let’s encrypt signed certificates for the domain.

A quick tip to make your life a bit easier with VSCode and Python.

In this post I’ll share the steps I did to deploy a SaaS Pegasus bootstrapped Django app (Scriv from the SaaS Pegasus marketplace to be precise) with Celery, Redis and Postgres on a Dokku host.

A quick note about the Furo theme for the Sphinx documentation system.

A workaround for transferring models to air-gapped Ollama instances.

A tutorial and video about installing and using Ollama and OpenWebUI on Windows.

How to summarize texts with LLMs that are too large for their context window.

Example Excel workbooks for a book about using OpenAI models in Excel Formulas.

Practical use cases of ChatGPT’s / GPT-4’s image input feature.

What are small LLMs good at and how to get good results from small LLMs.

How to install and use httpx.

Microsoft keeps adding new exciting features to Excel all the time.