Claude Code

Claude Code Updates

Last updated 2026-09-28

What's new

2026-09-28

Claude Code (a coding assistant that runs in your computer's terminal) and Computer Use (tools that let Claude interact with desktop applications) are two new applications built using the Claude API (a way for software to talk to Claude, an AI assistant).
These applications help you understand how to use the Claude API by showing you how to name inputs, see where the application works, and check the results.
The goal is to create a smaller, testable boundary between Claude and your application, making it easier to inspect and reuse.
This module is also a good practice for the Claude Certified Architect exam, which tests your knowledge of using Claude's tools.

2026-09-13

Rockbot (an email management system) works 24/7, even when your computer is off, unlike Claude Co-work (a previous email tool that only runs when your computer is on).
Rockbot uses its own server to manage your emails, keeping your sensitive information safe on your desktop.
To set up Rockbot, you need to download the app (around $20/month) and use a chat assistant like Claude (an AI tool you chat with) or Chat GBT (another AI chat tool) to create and train your email management bot.
Rockbot can connect to your Gmail (email service), Google Calendar (scheduling tool), and other apps to organize and manage your emails based on your preferences.

2026-09-04

Claude Code (a coding assistant tool) now offers a free model with 1.5 billion tokens monthly, a significant cost-saving for users previously paying for credits.
Omni Route (a laptop app) aggregates free API keys from multiple providers, automatically switching between them to maximize free usage, avoiding the hassle of manual configuration.
This setup allows users to keep the Claude Code interface while changing the underlying AI model (the "brain") to a free one, making it versatile for other tools like Deep Sea Carnage (another AI coding tool).

2026-08-31

Claude Code, an AI tool for coding, now lets different coding sessions (called agents) communicate with each other, sharing only the necessary information, making multitasking easier.
The default setting for Claude Code is now "auto mode," where the AI can automatically execute actions without constantly asking for permission, making coding workflows smoother and safer.
Claude Code has a new "concise" output style, which provides shorter responses, saving on token usage (the way AI measures text input and output) during long coding sessions.
The Claude Code desktop app now launches twice as fast, and there's a 50% increase in weekly usage limits, with plans to make this increase permanent.

2026-08-28

OpenAI's new chip, Jalapeno (a special computer part for AI tasks), is up to 100 times more efficient than Nvidia's best chips, according to their tests.
Anthropic (an AI company) released two new AI models briefly, which were tested and then removed, and they might be rolling out a new model, Fable 5.1, quietly.
Alibaba (a tech company) created a new AI model that costs much less to train than its previous one.
Claude (an AI assistant) fixed a frustrating issue with agents (AI tools that do tasks for you), making it easier to work with them.

2026-08-22

Claude (an AI tool for creating websites and graphics) can now use a new system to create consistent, high-quality designs across different formats like websites, posters, and emails.
The "design loop" feature in Claude uses multiple AI agents to refine and improve designs, ensuring they match your vision and stay on brief.
Higgsfield (a platform for image and video models) can be connected to Claude to create images and videos, making it easier to produce consistent content across different media.

2026-08-19

For AI tasks, bigger models aren't always better; medium settings like Claude Fable 5 Medium or Opus 5 Medium often give the best balance of cost and performance for most tasks.
When using AI tools like Claude Code, start by setting a clear goal and asking it to question you to fill in any gaps, rather than trying to provide every detail upfront.
AI tools have a "context window" (the amount of conversation it can remember at once), which affects both cost and performance, so it's important to manage this by starting new chats when it gets too full.
Tokens are like words in a conversation with AI; the more tokens used, the more it costs and the worse the AI performs, so it's important to keep track of this.

2026-07-25

A new way to make money with AI is becoming popular: becoming an AI consultant (someone who helps businesses use AI to solve problems and save time/money).
Instead of starting an AI agency (a business that sells AI services to clients), many people are now getting hired by companies to use AI tools like Claude (a type of AI) to improve their specific business.
Companies are struggling to use AI effectively, even though they're spending a lot of money on it, creating a big opportunity for skilled AI consultants.
There are two main ways to become an AI consultant: freelancing (working for yourself and finding your own clients) or getting hired by a company to use AI full-time.

2026-07-16

Claude (an AI assistant) can automate boring tasks, like sorting emails into categories (leads, urgent, etc.) and drafting responses, saving you 5-10 hours weekly.
For leads, Claude can research companies, draft replies, and even schedule meetings using your calendar, streamlining your sales process.
After client calls, Claude can generate branded PDF proposals with scope, pricing, and signatures, saving time on manual proposal creation.
This setup can be adapted to various jobs, especially those involving sales, marketing, or regular research tasks.

2026-07-13

Hermes (a free, open-source AI assistant) gained popularity for its strong memory, allowing it to remember past conversations, unlike Claude (a paid AI assistant) which struggles with this.
Hermes' success is due to its simple setup and better memory, with users praising its ability to recall past context, making it feel like a helpful colleague.
However, Hermes has some issues, like occasionally overwriting good information and requiring separate setup and maintenance, which can be complicated.
The speaker decided to create a similar memory system within Claude, keeping its benefits and fixing its issues, all without needing extra servers or subscriptions.

2026-07-04

Claude (an AI tool by Anthropic) is helping non-coders build real businesses, like Vulcan, which won a Virginia state contract for government software.
Claude Code (a feature of Claude) builds full apps, websites, or automates tasks in minutes, just by describing what you want in plain English.
Claude is "agentic" (it takes action on its own), works in parallel (multiple tasks at once), and remembers things, making it a powerful tool for businesses and jobs.
Over half of the startups in Y Combinator's (a famous startup accelerator) newest batch are building with Claude, showing its growing popularity and effectiveness.

2026-06-28

Claude (an AI assistant) is designed to make users feel productive, not necessarily make money, which can limit earnings by reducing output quality and speed.
Claude tends to agree with users too much, a trait researchers call "sycophant" or "yes man," which can lead to poor decisions; a tool called "roast" helps combat this by challenging ideas.
The "roast" tool creates a council of personas to stress test ideas, including a contrarian, expansionist, first principles thinker, deep researcher, buyer, and judge, providing a verdict and cheap test suggestions.
These upgrades aim to improve Claude's usefulness for business, such as building apps, running agencies, or AI consulting, by enhancing output quality and speed.

2026-06-25

Claude (an AI assistant) has three main modes: Chat (quick answers), Co-work (file access), and Code (full access, best for building things).
Opus 4.8 is Claude's most capable model, Sonnet 4.6 for daily tasks, and 4.5 for fast, simple work.
Connect Claude to tools like Gmail, Google Drive, or Firecrawl (a web data grabber) to boost productivity.
Use "sub agents" in Claude to multitask, getting 5-10 times more output in the same time.

2026-06-19

AI coding assistants (tools that help write and plan code) can handle large amounts of information, but they can still make mistakes, like sending emails to the wrong people.
You need to carefully plan and verify the work of AI coding assistants, as they might still find ways to do things you didn't explicitly allow.
Claude Code (a popular AI coding assistant) can be used as a "second brain" to help run your business, not just for coding.
AI tools and their uses are changing quickly, so it's important to stay updated and learn how to use them effectively.

2026-06-16

**Claude Code (AI tool that can do tasks for you)** is like a chatbot (AI that talks to you) but can also take actions, like creating files or connecting to your tools, without you doing it manually.
It uses a terminal (black screen with text), but you mostly interact with it like a chat window, and you can use a user-friendly interface instead.
To use it effectively, be specific with your instructions (called prompts) to get better results, and use a file called `claw.md` to set your preferences once, so you don't have to repeat them.
**Auto mode** lets Claude Code do routine tasks without asking for permission each time, only stopping you for important decisions, making it easier to use.

2026-06-10

**Claude Mythos 5 (a new, powerful AI model)** is now available, allowing users to set high-level goals and let the AI autonomously work towards them, rather than giving step-by-step instructions.
**Treat Claude like a thought partner (an equal collaborator)** and ask for its input before starting a project to leverage its advanced capabilities.
**Use loops (repeated tasks or processes)** to let Claude work continuously on complex projects, like building a comprehensive personal productivity app with multiple features.
**Access Claude Mythos 5** by typing `/modclaw-fable-5` in the command line interface (CLI, a text-based way to interact with software), even if it's not yet visible in the model picker or desktop app.

2026-06-07

**Multiple AI sessions**: Boris Sherny (the creator of Claude Code, an AI tool for coding) runs many AI sessions at once, each handling a single task, to boost productivity and avoid mixing contexts.
**Claude.md file**: This file stores rules and context for Claude Code, so you don't have to repeat instructions; it's like a cheat sheet that the AI checks every time it starts a session in that folder.
**Compound engineering loop**: By continuously updating the Claude.md file with new rules based on mistakes or lessons learned, the AI improves over time, making future sessions smarter and more efficient.
**Team collaboration**: Teams can share the same Claude.md file, so everyone benefits from the rules and improvements added by others, creating a shared knowledge base.

2026-06-03

Ralph loops (AI-powered automation tasks) are replacing complex workflow tools, letting you build smart automation directly in Claude Code (AI coding assistant).
Many programmers now use AI assistants like Claude Code to write all their code—a huge shift from six months ago when almost nobody worked this way.
These tools work beyond coding: people use them for emails, newsletters, calendars, and daily work, not just programming.
Building Ralph loops is practical and hands-on—you create working tools that save time, unlike brittle platforms like N8N (workflow automation software) that break regularly.

Key points

What it is

Claude Code is an AI coding tool by Anthropic that helps developers write, review, and fix code across many programming languages.
It uses a "harness" (a system guiding the AI’s decisions) to navigate errors, adapt, and learn from past failures, improving over time.
It offers features like persistent memory (long-term recall), parallel code review, and the ability to spawn multiple pull requests with one command.
It aims to close the "perception gap" where developers think they're faster when using AI, even if they're not.

How to use it

Update Claude Code by typing `claude update` in the terminal and pressing enter to grab the latest version.
Guide the AI's learning by using a **Claude.md file** (a Markdown file that stores your preferences and instructions) to help Claude understand your patterns.
Verify updates by opening a new terminal window and typing `claude`, or use VS Code for a visual environment.
Bundle updates using plugins, installing skills, hooks (scripts that run on events), agents, MCP connections (connections to other systems), and commands with one command each.

Watch out for

Failed attempts and broken code left in your session context (the conversation history Claude uses to understand your project) can waste tokens (units of text the model processes) and session time.
Vague prompts can lead to repeated corrections, so be specific with your instructions to help Claude learn and improve.
Avoid cluttering your prompts with detailed reference docs; instead, use your Claude.md file as a source of truth for persistent project instructions.

Tools named

Claude Code (an AI coding tool), Hookify (a tool that injects documentation into conversations)

Lesson 1: What is Claude Code Updates and why it matters

Claude Code Updates are the frequent improvements Anthropic ships to its AI coding tool, Claude Code. This matters for AI development because the tool now runs in production across multi-million line codebases, legacy systems, and languages like C, C++, C#, and Java — not just trendy languages. By April 2026, over 75,000 developers were using it on GitHub.

The core breakthrough is what Anthropic calls the harness (the system guiding the AI’s decisions). The harness matters more than the model itself. Older tools relied on retrieval (searching stored chunks of code at query time), which breaks at large scale because embedding pipelines can’t keep up with active teams. Claude Code solves this by having the AI itself navigate errors, adapt, and learn from previous failures — it becomes more informed over time without carrying old baggage.

A key update is persistent memory (long-term recall across sessions), letting agent teams remember past fixes and upgrades. Features now include parallel code review that fixes itself, one command spawning 30 pull requests, and sessions that teleport between cloud and terminal. Even the perception gap matters: one study found experienced developers using AI took 19% longer but thought they were 24% faster. Claude Code updates aim to close that gap.

For non-coders, it’s possible to build a first application in days. The tool keeps evolving rapidly — Claude Code 2.1.33 and 2.1.71 both shipped within weeks of each other.

Sources

Lesson 2: How to use Claude Code Updates: step-by-step

To update Claude Code and apply fixes, you start by running a single terminal command. Type `claude update` and press enter. This grabs the latest version — for example, version 2.1.72 was released with the ability to open Claude Code tabs programmatically. Over 75,000 developers build with Claude Code on GitHub, so updates roll out frequently.

After updating, Claude Code learns from past fixes and upgrades, making each fresh session more informed without carrying over old baggage. You can guide this learning by using a Claude.md file (a Markdown file that stores your preferences and instructions). Integrate it into your workflow and tell your .md file how you operate. This file becomes part of the iteration process, helping Claude understand your patterns and apply fixes consistently.

To verify the update worked, open a new terminal window and type `claude`. Claude Code will access your computer and show you which files it can see. For a cleaner interface, work inside VS Code — it provides a visual environment instead of a raw terminal. When Claude proposes a fix or change, it shows you a step-by-step plan. You can highlight any part, add a comment, and make suggestions before accepting.

For maximum efficiency, bundle your updates using plugins. Skills, hooks (scripts that run on events), agents, MCP connections, and commands can all be installed with one command each. In under five minutes, your full Claude Code stack is ready with all updates enforced.

Sources

Lesson 3: Best practices and pitfalls

Claude Code updates come fast. Run `claude update` to grab version 2.1.71 or 2.1.72 — over 75,000 developers are building with these releases on GitHub. A major pitfall is letting failed attempts and broken code stay in your session context (the conversation history Claude uses to understand your project). Every failed attempt you leave in context costs you tokens (units of text the model processes) and session time, making your subscription less efficient. The best practice: clear the context or open a fresh session when Claude does something wrong, instead of just saying "That didn't work, try this."

Another common mistake is making vague prompts like "Add this... no, I wanted this instead." Claude learns from your corrections. If you repeatedly correct the same issue, Claude can autogenerate a rule from those fixes — your frustrations become permanent guardrails. Use Claude.md files, which are plain text files that give Claude persistent project instructions so you don't waste thousands of tokens on every new conversation getting Claude caught up.

A huge time-saver is using Hookify, a tool that reads all current documentation and injects it into the conversation before Claude writes code. Without it, Claude can repeat mistakes you already corrected. Your Claude.md is your source of truth — treat it as never-forget rules that Claude reads every time. Detailed reference docs belong there, not cluttering your prompts. Fixes and upgrades accumulate, so Claude learns from failures and ships updates without old baggage.

Sources