George

Yay, my Claude Max $100 plan weekly limit reset, giving Claude Sonnet 4.6 a good run after playing with GLM-5 in Claude Code for past 3 days 🤓

Claude Code 2.1.49 github.com/anthropics/c...

YouTube video by Lenny's Podcast Head of Claude Code: What happens after coding is solved | Boris Cherny

Boris Cherny creator of Claude Code - What happens after coding is solved? www.youtube.com/watch?v=We7B...

Hit my Claude Max $100 weekly limits 4 days into the week meant I had 3 days to focus solely on GLM-5 + Claude Code realising GLM-5 needs way more prompt steering for same task as Opus/Sonnet 4.6. Spent 3 days improve Claude Skill/Agent md files & improved GLM results from 80% to 97% of Opus 4.6

YouTube video by Bijan Bowen Gemini 3.1 Pro Is HERE – Hands-On With Google’s Newest Model!

Bijan Bowen checking out Google Gemini 3.1 Pro www.youtube.com/watch?v=ODPa...

Google Gemini 3.1 Pro in Google AI Studio

Google Gemini 3.1 Pro already ranking on arena.ai - text LongQuery rank

Google Gemini 3.1 Pro already ranking on arena.ai

Google Gemini 3.1 Pro already ranking on arena.ai

Google Gemini 3.1 Pro is available in Github Copilot Pro plan but it seems to be experiencing high demand

Google Gemini 3.1 Pro available in Perplexity Pro 🤓

Gemini 3.1 Pro Preview - API, Providers, Stats Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows...

Google Gemini 3.1 Pro on OpenRouter AI openrouter.ai/google/gemin... 🤓

Gemini 3.1 Pro: A smarter model for your most complex tasks 3.1 Pro is designed for tasks where a simple answer isn’t enough.

Google Gemini 3.1 Pro in the house blog.google/innovation-a... 🤓

Perplexity Pro adds Anthropic Claude Opus 4.6 & Claude Sonnet 4.6 🤓

Perplexity Pro adds Anthropic Claude Opus 4.6 & Claude Sonnet 4.6 🤓

Guess which AI LLM model generated this? 🤓

Claude Code 2.1.47 release - longest bug fix list github.com/anthropics/c... 🤓

Today ran out of Claude Max $100 weekly limits and need to wait 3 days for reset, so focusing on driving GLM-5 within Claude Code 🤓

YouTube video by Bijan Bowen Claude Sonnet 4.6 Is INSANE – Hands-On With Anthropic’s New Model!

Claude Sonnet 4.6 tests www.youtube.com/watch?v=sXCn...

With Claude Sonnet 4.6 and Opus 4.6 released, it will be an interesting next 3 days while I focus on using GLM-5 Coding Pro plan within Claude Code while waiting for the weekly quota to rest 😆

Did Claude Opus 4.6 help train Claude Sonnet 4.6? 🤔

Can anyone comprehend the level of collective investment required to develop OpenAI GPT-5.3, Anthropic Claude Opus 4.6/Sonnet 4.6, DeepSeek V4, QWEN 3.5, GLM 5, Grok 4.2? 🤔😲

Claude Code turns 1yrs old. Happy Birthday - folks celebrate and play Claude Invaders space-invaders.centminmod.com 🤓

Claude Code with Opus 4.6 and Sonnet 4.6 access to 1 million context now, but look at those prices - $10/37.50 and $6/22.50 respectively per 1 million tokens 😲

GLM-5 for code security analysis within Claude Code is around 80% of Opus 4.6 out of the box. After optimisation of prompt steering instructions, it's at 80-85%. Then add RE2 (re-read) prompt optimisation techniques + more detailed script calls from Skill md file, GLM-5 is at 85-95% of Opus 4.6 🤓

Yup need to stretch it originally as ran out of Claude Code weekly limits 4 data into the week 😂

So Anthropic has Opus 4.6 and Sonnet 4.6, now all we need to complete the set is Haiku 4.6 🤓

GitHub - centminmod/explain-openclaw: Multi-AI documentation for OpenClaw: architecture, security audits, deployment guide Multi-AI documentation for OpenClaw: architecture, security audits, deployment guide - centminmod/explain-openclaw

github.com/centminmod/e...

Anthropic just released Claude Sonnet 4.6 with extra usage enabled 1 million token context window too 😎

Running low on my Claude Code Max $100 weekly usage limits for tracking OpenClaw code and security developments on my Explain OpenClaw GitHub repo so been testing GLM-5 Coding Pro plan $10.80/month within Claude Code with custom agents launched from SKILL md files. When it works 🤓