CODE

LLM-Assisted Coding Quote Sparks Controversy and Misinterpretation

By

–

31 July 2025 18h36

This quote turned out to be way more controversial than I expected! I think a bunch of people instantly reacted to it as an argument against any form of LLM-assisted coding at all – without reading the (only slightly longer) piece the quote came from to understand the context

→ View original post on X — @skirano

Best Model for Optical Character Recognition Tasks

By

@skirano

–

31 July 2025 18h34

Not at all, it's just the best model for OCR

CEOs and Technical Debt: Understanding Future Payment Obligations

By

–

31 July 2025 18h29

CEOs take on technical debt all the time, that's why it's a useful metaphor: you can chose to take on technical debt, but you have to acknowledge that payments will come due

→ View original post on X — @skirano

Mistral OCR App Converts Images PDFs to Markdown

By

@skirano

–

31 July 2025 18h06

I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR.

It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown.

All you need is a @MistralAI API. pic.twitter.com/cUcraPsD56
— Pietro Schirano (@skirano) 31 juillet 2025

I needed an app to export markdown from images and PDFs, so I built one using the best model on the market: Mistral OCR. It can convert images, PDFs, and even extract tables and images, keeping them contextually within the markdown. All you need is a @MistralAI API.

MLX Model Requires 96GB RAM, Runs Space Invaders Game

By

–

31 July 2025 17h45

This full precision MLX model needs 63.5GB of RAM while running (so likely needs a Mac with 96GB or 128GB) – but its space invaders is fully functional! https://t.co/0TVkYrAIxV
— Simon Willison (@simonw) 31 juillet 2025

This full precision MLX model needs 63.5GB of RAM while running (so likely needs a Mac with 96GB or 128GB) – but its space invaders is fully functional!

4-bit Quantized Qwen3 Coder Model Runs Space Invaders

By

–

31 July 2025 17h41

Looks like this 4bit quantized MLX model uses about 35GB ofRAM to run a prompt and produces an almost-working space invaders https://t.co/S9b64sxYlq https://t.co/y8k0SspsgM
— Simon Willison (@simonw) 31 juillet 2025

Looks like this 4bit quantized MLX model uses about 35GB ofRAM to run a prompt and produces an almost-working space invaders https://
huggingface.co/mlx-community/
Qwen3-Coder-30B-A3B-Instruct-4bit
…

→ View original post on X — @testingcatalog

Manus AI launches Wide Research for parallel processing

By

@testingcatalog

–

31 July 2025 17h32

Manus AI introduced Wide Research 🤖

"Wide Research is a system-level mechanism for parallel processing, and a protocol for agent-to-agent collaboration." https://t.co/z6DH8z5sFR pic.twitter.com/bjrTgCThsL
— 🚨 AI News | TestingCatalog (@testingcatalog) 31 juillet 2025

Manus AI introduced Wide Research "Wide Research is a system-level mechanism for parallel processing, and a protocol for agent-to-agent collaboration."