Introducing Sonnet 4.6

73 posts tagged ‘llm-pricing’. Posts about the pricing of various LLMs. See also my pricing calculator.

Opus 4.6 is much smarter than the other one. It feels like I’m working with someone from Bronx Science. I had been using Sonnet 4.6, which I switched to after reading somewhere that it costs …

114 posts tagged ‘pelican-riding-a-bicycle’. My benchmark for LLMs: "Generate an SVG of a pelican riding a bicycle". Here's my answer to what happens if AI labs train for pelicans riding bicycles?. "User …

Sonnet 4.6 is out today, and Anthropic claim it offers similar performance to November's Opus 4.5 while maintaining the Sonnet pricing of $3/million input and $15/million output tokens (the Opus …

Explain Google AI credits

113 posts tagged ‘pelican-riding-a-bicycle’. My benchmark for LLMs: "Generate an SVG of a pelican riding a bicycle". Here's my answer to what happens if AI labs train for pelicans riding bicycles?. "User …

Gemini 3.1 Pro, Claude Sonnet 4.6, Grok 4.20 and more dropped in February 2026. We rank the best AI models, benchmarks & break down costs.

113 posts tagged ‘pelican-riding-a-bicycle’. My benchmark for LLMs: "Generate an SVG of a pelican riding a bicycle". Here's my answer to what happens if AI labs train for pelicans riding bicycles?. "User …

What dev tools do Claude Code, Codex, and Cursor actually recommend? Systematic research across real repos and model generations.

Our Magazine HACKER BITS is the monthly magazine that gives you the hottest technology stories straight from Hacker News. We select from the top voted stories for you and email them to you in an easy-to-read email magazine format. hacker ... Read More

113 posts tagged ‘pelican-riding-a-bicycle’. My benchmark for LLMs: "Generate an SVG of a pelican riding a bicycle". Here's my answer to what happens if AI labs train for pelicans riding bicycles?. "User …

Jason's Game Of Life (aka Land Grab Simulator). Contribute to codercowboy/landgrabsim development by creating an account on GitHub.

AI Coding Assistants and Agents are changing the way software is created, but developers have been expected to learn how to use them without any guidance. As managers push developers into adopting these tools how are they expected to avoid the dangers and pitfalls of vibe coding? In this post I take a high level look at the tools and practices developers can use to move quickly with AI without wanting to set their code bases on fire.

A data-driven comparison of agentic coding stacks: Hermes Agent with Qwen3.6 Plus vs Claude Code Max 20x — 95% of the quality, half the cost, with built-in provider failover.

I went on a weekend trip. I came back to a new Claude, a new GPT and an existential crisis. The pace of AI is no longer monthly. It's weekly.

Claude Sonnet 4.6 Released - I am all-in on the Claude train at the moment. Sonnet 4.6 has raised my expectation for other “default” frontier models. Anthropic seems to want to eliminate low-skill office work with these models. Useful? Yes. Potentially dangerous to society? Absolutely. It’s Not Just You - the iOS keyboard is broken - As an Apple user, I’ve been annoyed for a decade at how bad the keyboard on iOS is. This video is proof I’m not the only one having issues with it. FOSDEM 2025 - The Road to Mainstream Matrix - I flirted with the Matrix protocol in 2019 as I was searching for a persistent alternative to IRC that wasn’t Discord. I want Matrix to succeed, but I’ve also been curious why it hasn’t seemed to take off. This video explains the trouble that project is facing. That’s all for this week! God bless.

Anthropic’s latest model brings Opus-level reasoning to a mid-tier price point. We analyze the technical leaps, the lingering security flaws, and the community’

Welcome to issue 123 of Hacker Bits! We have a fantastic lineup this month spanning AI-assisted development and its limits, the human side of technical leadership, time handling in JavaScript, a rogue AI security incident and some honest reflection on ... Read More

Practical guidance for developers building computer and browser use integrations with the Claude model family.

199 posts tagged ‘llm-release’. New releases of various LLMs.

112 posts tagged ‘claude-code’. Claude Code is Anthropic's terminal coding agent, enabling Claude to run tools in a loop on your own machine.

tars is a personal AI assistant with CLI, Web UI, Email, and Telegram channels, persistent memory, hybrid search, integration with tools I used all the time. About 35 features, 14kloc of python and 600 tests all told. I didn't write any of it. The experience was different enough from traditional de

The Value of Software Development Is (near) Zero