RSSAmplifier

Blog

P. Galeone's blog

Let the machines learn

pgaleone.euRSS feed ↗10 posts

Latest posts

Use Your Brain: Engineering Standards in the Age of LLMs

Software development is not a niche anymore. The advent of LLMs made it possible for everyone to write their own software - and this is a good thing. However, I see a huge number of software engineers (the real ones!) falling into the vibe-coding trap. Those people were used to design - think! - and later implement. Now, instead, they are just producing a huge amount of dubious quality code,…

Paying Google to Hack macOS Users?

There is a horrible trend in the software industry: installing software with curl | shell . People are encouraged to blindly execute scripts downloaded from the internet. What could go wrong? Software, like many other fields, moves following trends. When disruptive projects such as OpenClaw tell you to install with curl -fsSL https://openclaw.ai/install.sh | bash , and even giants like NVIDIA…

Digital Excommunication

I was listening to a Radio24 program 1 and the topic immediately struck me. The episode is titled “La scomunica digitale” 2 (Italian for Digital Excommunication ). In that episode, the radio host introduced the case of Nicolas Guillou 3 , a French ICC judge sanctioned by the Trump administration. This sanction is a ban from US territory, but it also prohibits any American individual or legal…

Gemini-Powered Stock Analysis: Parsing Financial News for Automated Trading Decisions

Over the past weeks I built a small Go service that reads Italian finance RSS feeds, extracts the article body, and asks Gemini for a buy/sell/hold view for the tickers it finds. Below I show the pieces that make it work and the trade‑offs I hit along the way. This runs inside a broader trading setup that talks to a broker API. I’m working on software to automate trading on a well‑known Italian…

From Vertex AI SDK to Google Gen AI SDK: Service Account Authentication for Python and Go

On June 25th, 2025, Google sent an important announcement to all Vertex AI users: the Google Gen AI SDK has become the new preferred method for accessing generative models on Vertex AI. While Google provided a Vertex AI SDK migration guide to help with the transition, there’s a critical gap in the documentation—it doesn’t adequately cover authentication using service accounts, which many…

Getting back to the EU: from Google Cloud to Self-Hosted EU Infrastructure

In this article I’m going to show the process I followed to migrate some of the services I used from Google Cloud to an European provider, in this case OVH . I won’t use their cloud solution, but their VPS offering instead, in order to have full control over the infrastructure. 1 In particular, I will show how I moved out from Cloud SQL to a self hosted instance of PostgreSQL , how I moved the…

Using AI for Coding: My Journey with Cline and Large Language Models

In recent months, I embarked on a journey to transform the UI/UX of a side project— bot.eofferte.eu , a SaaS platform that automates Amazon affiliate marketing on Telegram and streamlines the Amazon Associates onboarding process. The project’s architecture is straightforward: a Go backend powered by the labstack/echo framework, with UI rendering handled by Go’s standard html/template package. To…

Fixing the code signing and notarization issues of Unreal Engine (5.3+) projects

Starting from Unreal Engine 5.3, Epic Games added support for the so-called modern Xcode workflow . This workflow allows the Unreal Build Tool (UBT) to be more consistent with the standard Xcode app projects, and to be compliant with the Apple requirements for distributing applications… In theory! 😅 In practice this workflow is flawed: both the code signing and the framework supports are not…

The (Hidden?) Costs of Vertex AI Resource Pools: A Cautionary Tale

In the article Custom model training & deployment on Google Cloud using Vertex AI in Go we explored how to leverage Go to create a resource pool and train a machine learning model using Vertex AI’s allocated resources. While this approach offers flexibility, there’s a crucial aspect to consider: the cost implications of resource pools. This article details my experience with a sudden price…

Building a RAG for tabular data in Go with PostgreSQL & Gemini

Large Language Models (LLMs) are well-suited for working with non-structured data. So far, their usage with structured data hasn’t been explored in depth although structured data is everywhere relational databases are. Making an LLM able to interact with a relational database can be an interesting idea since it will unlock the possibility of letting a user “chat with the data” and let the LLM…