Llm Articles
Page 1 of 4
(63 articles)
12/10/2025
•
EN
The Normalization of Deviance in AI
Explores the 'Normalization of Deviance' concept in AI safety, warning against complacency with LLM vulnerabilities like prompt injection.
12/10/2025
•
EN
Devstral 2
Mistral AI releases Devstral 2 and Devstral Small 2, two new open models focused on powering coding agents and software development tasks.
12/10/2025
•
EN
Under the hood of Canada Spends with Brendan Samek
An interview about Canada Spends, a project using Datasette, SQLite, and LLMs to make Canadian government financial data accessible and explorable.
12/9/2025
•
EN
Quoting Claude
A blog post analyzing a critical bug in Claude Code where a command accidentally deleted a user's home directory.
12/9/2025
•
EN
Prediction: AI will make formal verification go mainstream
AI is predicted to bring formal verification tools like Dafny and Verus into mainstream use, aided by LLMs making them more accessible.
12/7/2025
•
EN
Using LLMs at Oxide
Bryan Cantrill discusses applying Large Language Models (LLMs) at Oxide, evaluating them against the company's core values.
12/7/2025
•
EN
Quoting David Crespo
Tips from David Crespo on effectively using Claude Code for understanding codebases and automating tedious coding tasks.
12/3/2025
•
EN
A Technical Tour of the DeepSeek Models from V3 to V3.2
A technical analysis of the DeepSeek model series, from V3 to the latest V3.2, covering architecture, performance, and release timeline.
12/2/2025
•
EN
Claude 4.5 Opus' Soul Document
Anthropic's internal 'soul document' used to train Claude 4.5 Opus's personality and values has been confirmed and partially revealed.
11/27/2025
•
EN
deepseek-ai/DeepSeek-Math-V2
DeepSeek-Math-V2 is an open-source 685B parameter AI model that achieves gold medal performance on mathematical Olympiad problems.
11/25/2025
•
EN
llm-anthropic 0.23
Release of llm-anthropic 0.23 plugin adding support for Claude Opus 4.5 and its new thinking_effort option.
11/25/2025
•
EN
Quoting Claude Opus 4.5 system prompt
Analysis of a leaked system prompt for Claude Opus 4.5, discussing its content and the challenges of evaluating new LLMs.
11/23/2025
•
EN
Agent design is still hard
Armin Ronacher discusses challenges in AI agent design, including abstraction issues, testing difficulties, and API synchronization problems.
11/21/2025
•
EN
Non-determinism and ownership
A developer discusses the non-deterministic nature of LLMs like GitHub Copilot, arguing that while useful, they cannot take ownership of errors like a human teammate.
11/19/2025
•
EN
Fragments Nov 19
Martin Fowler discusses the latest Thoughtworks Technology Radar, AI's impact on programming, and his recent tech talks in Europe.
11/19/2025
•
EN
llm-gemini 0.27
New release of the llm-gemini plugin adds support for nested Pydantic schemas, YouTube URL attachments, and the latest Gemini 3 Pro model.
11/18/2025
•
EN
Connector-Based RAG With Live Confluence Data
A guide to building a connector-based RAG system that fetches live data from Confluence using its REST API and Java, avoiding stale embeddings.
11/18/2025
•
EN
The fate of “small” open source
Discusses the future of small open source libraries in the age of LLMs, questioning their relevance when AI can generate specific code.
11/15/2025
•
EN
llm-anthropic 0.22
Release of llm-anthropic plugin 0.22 with support for Claude's structured outputs and web search tool integration.