The daily ledger

Quoting voxium

It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code.…

MCP was always a bad idea?

My comment on MCP was always a bad idea? — Hacker News. This article entirely misses the value that MCP brings today. Sure, there's almost no reason to use MCPs if you are running a full-blown terminal agent (Claude…

llm-keys-ui 0.1

Release: llm-keys-ui 0.1 This plugin solves a very specific problem. I've started using Codex Remote to run coding agents on various machines while controlling them from my phone. Sometimes I use those machines to hack…

datasette-explain 0.2.2

Release: datasette-explain 0.2.2 Explain plans now work on read-only stored-query pages. I upgraded datasette.simonwillison.net to Datasette 1.0a40, which inspired me to ship a new version of this explain plugin. Tags:…

Plugin4Shell và CVE-2026-42559: hai lỗ hổng agent cần vá

Originally published on NextFuture Hai lỗ hổng công bố trong tuần đều nhắm vào cùng một điểm mù: agent tin vào thứ nó yêu cầu, không phải thứ nó thực sự nhận được. Plugin4Shell: ghim SHA không có nghĩa là an toàn Theo…

OwlLayer AI: Letting AI Agents Act on Your UI Instead of Replacing It

Most AI-in-product integrations fall into two camps, and both have a ceiling. A chatbot bolted onto the side of your app can talk, but it can't act - it has no real connection to your components, your state, or your…

🙀 Gemini broke into 3 real companies during a safety test

Cache key do LLM sinh: lỗi tách tenant chờ sẵn ở backend

Originally published on NextFuture Backend agent của bạn gọi model để tóm tắt mỗi request, rồi lấy chính chuỗi tóm tắt đó làm cache key. Hai tenant có giỏ hàng gần giống nhau sinh ra cụm từ gần giống nhau, key space sập…

Everything That Happened in AI This Weekend (September 18-19, 2026)

Google’s Gemini logged into three real companies during a cyber test, Anthropic juggled a new model and IPO timing, and Washington jumped directly into the AI copyright fight.

GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns

Beyond basic graph retrieval: six production-oriented architectures for combining semantic search, knowledge graphs, and LLM reasoning. The post GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns…

CBAM Paper Walkthrough: The Double-Attention Mechanism

Understanding and implementing CBAM (Convolutional Block Attention Module) from scratch with PyTorch The post CBAM Paper Walkthrough: The Double-Attention Mechanism appeared first on Towards Data Science.

Inside the megakernel serving engine for North Mini Code

A technical deep dive into how Cohere’s approach to megakernels delivers 1.58x faster LLM serving on H100 devices.

Turn SQLite Into A Vector Database For RAG

This video demonstrates how to turn SQLite into a vector database for AI applications using the sqlite-vec and sqlite-ai-vector extensions. It covers setting up both packages in Python with OpenAI embeddings,…

TPU Inference Externalization Full Steam Ahead

The article examines Google’s push to make TPUs a first-class platform for external LLM inference, including TorchTPU, vLLM, SGLang, and a rapidly maturing open software stack. Benchmarks TPUv7 Ironwood against NVIDIA…

NPC-Forge

NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs.

Alibaba Open Sources OpenCodeReview for AI-Assisted Code Review

Alibaba recently open-sourced OpenCodeReview, an AI-powered code review CLI that combines deterministic pipelines for file selection, bundling, and rule matching with an LLM agent for dynamic code analysis. It supports…

Jev and LLMs: who does what?

How Jev handles structured decisions, with a minimal example and eight early projects. After two years in stealth, Diogo Almeida, one of the researchers behind ChatGPT, launched Jev at TypeSafe AI. The company…

No GPU, No Problem: Flagship LLMs on a GPU-less Teenaged Server

There are lots of reasons to run LLMs locally, from privacy concerns to just wanting to futz about with the technology, but if you want to run the big models, …read more

Structured Output in the browser with Transformers.js 4.3

Structured output is here. The new @huggingface/transformers-structured-output package hooks into token generation and makes sure every token follows your JSON Schema or regex. Full walkthrough in the linked video. npm:…

Trump Says He’s Forming a U.S. ‘AI Force’ and Will Name an AI Czar

Trump says he is forming a U.S. AI Force and will name an AI czar. Here’s how it could develop and how it fits into the Pentagon’s existing AI-first military strategy.