I put together these annotated slides from my five minute lightning talk at PyCon US 2026, using the latest iteration of my annotated presentation tool.
#
I presented this lightning talk at PyCon US 2026, attempting to summarize the last …
Enterprises deploying LLMs have spent the past two years building defenses around a reasonable assumption: malicious behavior leaves a trace in the input. Scan for suspicious tokens, filter unusual characters, watch for prompt injection patterns. New r…
GDS weighs in on the NHS's decision to retreat from Open Source
Terence Eden continues his coverage of the NHS’ poorly considered decision to close down access to their open source repositories in response to vulnerabilities reported to them…
From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs
Tool: QR code generator
Claude helped me build this tool for creating QR codes, for both text/URLs and for connecting to WiFi networks.
Tags: vibe-coding, tools, generative-ai, ai, llms
This Mitchell Hashimoto quote about Bun migrating from Zig to Rust reminded me of a similar conversation I had at a conference last week.
I was talking to someone who worked for a medium sized technology company with a pair of legacy/legendary iPh…
[…] On the interesting side is how fungible programming languages are nowadays. Programming languages used to be LOCK IN, and they’re increasingly not so. You think the Bun rewrite in Rust is good for Rust? Bun has shown they can be in probably …
Welcome to the Datasette blog
We have a bunch of neat Datasette announcements in the pipeline so we decided it was time the project grew an official blog.
I built this using OpenAI Codex desktop, which turns out to have the Markdown session trans…
Release: llm 0.32a2
A bunch of useful stuff in this LLM alpha, but the most important detail is this one:
Most reasoning-capable OpenAI models now use the /v1/responses endpoint instead of /v1/chat/completions. This enables inter…
A year ago, frontier models started losing track of instructions somewhere around 200–300 simultaneous constraints. With 2026 models, that ceiling is closer to 2,000 — an order-of-magnitude jump. We re-ran IFScale to see how, and how each model fails.
The post Models got an order of magnitude better at following instructions in one year appeared first on Arize AI.