llm-gemini 0.37
Release: llm-gemini 0.37 Google launched Gemini 4 Hydrogen today - the lowest cost member of the Gemini 4 family. It's actually not too far off the price of its much bigger siblings, Carbon and Argon. I'm finding Gemini…
Topic - Edition
Python
RAG Retrieval Lost 40 Points When Distracting Passages Grew to 2.68M
A reproducible test of BM25, embeddings, and parent documents shows why author-written evals overrate search, and why answer position in context matters. The post RAG Retrieval Lost 40 Points When Distracting Passages…
I Mutation-Tested 50 Python Libraries. Tests in the Young Ones Missed 41% of Planted Faults.
Across 2,312 planted faults the study also surfaced four real library problems, from a Windows data-loss bug to README examples that do not work as written. The post I Mutation-Tested 50 Python Libraries. Tests in the…
Security updates for Thursday
Security updates have been issued by Debian (aodh, apache2, dnspython, firefox-esr, mutt, octavia, spip, thunderbird, and watcher), Fedora (epiphany, firefox, freerdp, java-25-openjdk, java-latest-openjdk, libsoup3,…
Learn With Mentor AI: Working Through a Coding Exercise
Learn how to use Mentor AI on a Real Python coding exercise. Ask why a test failed, get hints instead of the answer, and check your understanding.
A Soft-Label MNIST Testbed for Human vs. Model Confidence
Annotators marked each MNIST and Mukhoti digit yes, no, or unsure, producing image-level soft labels and uncertainty scores. The post A Soft-Label MNIST Testbed for Human vs. Model Confidence appeared first on Towards…
Scoping `sys.monitoring.restart_events()` to a single tool
Hi everyone, I’d like to start a discussion about scoping sys.monitoring.restart_events() to a single tool. sys.monitoring is designed so multiple tools can share an interpreter, and almost all of the API is scoped by…
How to Read Cross Pair Correlation in R Without Fake Repulsion (Part 3)
A simulated scar and data from 31 animals after ischemia show how an inhomogeneous estimator, random labelling, and brms separate tissue loss from real interaction. The post How to Read Cross Pair Correlation in R…
Quiz: Learn With Mentor AI: Working Through a Coding Exercise
Practice getting unstuck on a Python coding exercise with Mentor AI, from mutable default arguments to checking for None with is.
Luke Plant: Why I’m calling your contribution “slop”
You have probably arrived at this web page because you have attempted to contribute to an Open Source software project, probably via a Pull Request and I, or perhaps someone else, has called your efforts “slop” and…
LernerPython blog, from Reuven Lerner: Announcing: Vibe to valid
Vibe coding is fun: You can go from an idea to a working app in a weekend. But if you don’t have a background in software, how can you be sure your app is secure? Tested? Backed up? Ready for real customers, or for an…
PyPy: 20 Years of Pyrolog
On November 12, 2006 I did the first surviving commit of my RPython based Prolog implementation Pyrolog into the PyPy repository. I had been working on it since spring 2006 already. In that year we were finishing up the…
Tryton News: Release 0.3.0 of tryton-filestore-cellar
We are proud to announce the release of tryton-filestore-cellar version 0.3.0. tryton-filestore-cellar is Tryton’s filestore implementation based on the Cellar storage service. In addition to bug fixes, this release…
Statically tracked exceptions in Python's type system to support EAFP
Python has historically considered the EAFP pattern to be more idiomatic, where a program might perform an unsafe operation, catching and handling the resulting exception: client: User | Client | None try: name =…
Graham Dumpleton: Muru: releases, not restarts
With the previous post I finished with development mode. Something I kept coming back to in those posts was that when muructl run reloads after a change, it isn't restarting anything. It starts a new release beside the…
Adapting CPython for yk