Anthropic Courses
Learn to build with Claude through Anthropic's comprehensive courses and training programs.
llms
Alibaba's small, open source Qwen3.5-9B beats OpenAI's gpt-oss-120B and can run on standard laptops
Whether it is a 0.8B model running on a smartphone or a 9B model powering a coding terminal, the Qwen3.5 series is effectively democratizing the "agentic era."
microgpt
Musings of a Computer Scientist.
Switch to Claude without starting over | Claude
Transfer your preferences, projects, and context from other AI providers into Claude. Switch without losing what makes your AI useful.
Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers | Hacker News
Alibaba's new open source Qwen3.5 Medium model offers near Sonnet 4.5 performance on local computers
This leap is made possible by near-lossless accuracy under 4-bit weight and KV cache quantization, allowing developers to process massive datasets without server-grade infrastructure.
Claude Code Remote Control
New Claude Code feature dropped yesterday: you can now run a "remote control" session on your computer and then use the Claude Code for web interfaces (on web, iOS and โฆ
Anthropic just released a mobile version of Claude Code called Remote Control
Unofficial solutions, while functional, were often brittle and prone to timeout issues. Remote Control replaces these workarounds with a native streaming connection
IBM's $40B stock wipeout is built on a misconception: Translating COBOL isn't the same as modernizing it
Investors wiped $40 billion from IBM's market cap after Anthropic released COBOL translation tools. Analysts say the market got the news right and the conclusion wrong.
Getting Started
Start building AI apps in Ruby in 5 minutes. Chat, generate images, create embeddings - all with one gem.
Ruby Is the Best Language for Building AI Apps
A pragmatic, code-first argument for Ruby as the best language to ship AI products in 2026.
๐๐น๐ฎ๐๐ฑ๐ฒ ๐ฆ๐ธ๐ถ๐น๐น๐ ๐ถ๐ ๐ฝ๐ฟ๐ผ๐ฏ๐ฎ๐ฏ๐น๐ ๐๐ต๐ฒ ๐บ๐ผ๐๐ ๐๐ป๐ฑ๐ฒ๐ฟ๐ฟ๐ฎ๐๐ฒ๐ฑ ๐ณ๐ฒ๐ฎ๐๐๐ฟ๐ฒ ๐๐น๐ฎ๐๐ฑ๐ฒ ๐ต๐ฎ๐ ๐ฏ๐๐ถ๐น๐. If youโre still writing the same prompts in Claude every dayโฆ |โฆ
๐๐น๐ฎ๐๐ฑ๐ฒ ๐ฆ๐ธ๐ถ๐น๐น๐ ๐ถ๐ ๐ฝ๐ฟ๐ผ๐ฏ๐ฎ๐ฏ๐น๐ ๐๐ต๐ฒ ๐บ๐ผ๐๐ ๐๐ป๐ฑ๐ฒ๐ฟ๐ฟ๐ฎ๐๐ฒ๐ฑ ๐ณ๐ฒ๐ฎ๐๐๐ฟ๐ฒ ๐๐น๐ฎ๐๐ฑ๐ฒ ๐ต๐ฎ๐ ๐ฏ๐๐ถ๐น๐. If youโre still writing the same prompts in Claude every day, youโre doing extra work. Skills fix that. They package your best instructions once, then you reuse them on demand. Result: less repetition, moreโฆ
chat jimmy
chat jimmy LLM web interface
The Claude C Compiler: What It Reveals About the Future of Software
On February 5th Anthropic's Nicholas Carlini wrote about a project to use parallel Claudes to build a C compiler on top of the brand new Opus 4.6 Chris Lattner (Swift, โฆ
Taalas is replacing programmable GPUs with hardwired AI chips to achieve 17,000 tokens per second for ubiquitous inference - MarkTechPost
We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them - Quesma Blog
BinaryAudit benchmarks AI agents using Ghidra to find backdoors in compiled binaries of real open-source servers, proxies, and network infrastructure.
We were surprised that todayโs AI agents can detect some hidden backdoors in binaries. We hadnโt expected them to possess such specialized reverse engineering capabilities. However, this approach is not ready for production. Even the best model, Claude Opus 4.6, found relatively obvious backdoorsโฆ
https://garryslist.org/posts/half-the-ai-agent-market-is-one-category-the-rest-is-wide-open
๐ฃ(Claude Code Beginners Guide) Multi-Agent Orchestration: Run Claude Code Like a 5-Person Team | Notion
Quick note before you jump in:
The Critical Detail About AI That Separates Good Investments from Expensive Mistakes
You've heard the pitch. "We're going to add AI to the platform.
The Complete Hugging Face Primer for 2026
A practical 2026 guide to Hugging Face. Explore transformers, datasets, sentiment analysis, APIs, fine-tuning, and deployment with Python.
Today, the Hugging Face Hub hosts millions of pre-trained models, hundreds of thousands of datasets, and large collections of demo applications, all contributed by a global community.
Spaces: this is where you can build and host your demo, using Gradio and Streamlit.
Alibaba unveils new Qwen3.5 model for 'agentic AI era'
Alibaba on Monday unveiled a new artificial intelligence model Qwen 3.5 designed to execute complex tasks independently, with big improvements in performance and cost that the Chinese tech giant claims beat major U.S. rival models on several benchmarks.
Claude Code Tips From the Guy Who Built It
Boris Cherny created Claude Code at Anthropic. Over three Twitter threads (early January, late January, and February 2026), he shared how he and the Claude Code team use it every day. His setup is, in his own words, "surprisingly vanilla." I've pulled together every tip from allโฆ
Nvidiaโs new technique cuts LLM reasoning costs by 8x without losing accuracy
Nvidia researchers developed dynamic memory sparsification (DMS), a technique that compresses the KV cache in large language models by up to 8x while maintaining reasoning accuracy โ and it can be retrofitted onto existing models in hours.
OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491
Peter Steinberger is the creator of OpenClaw, an open-source AI agent framework that's the fastest-growing project in GitHub history.Thank you for listening ...
'Observational memory' cuts AI agent costs 10x and outscores RAG on long-context benchmarks
As AI agents move into production, teams are rethinking memory. Mastraโs open-source observational memory shows how stable context can outperform RAG while cutting token costs.
Claude Code for Everything: The Best Personal Assistant Remembers Things About You (A CLAUDE.md Deep Dive)
How CLAUDE.md files give Claude the context it needs to be effective, automatically, every session
Google just open-sourced their MCP server for databases. Connect any database to any AI agent in 10 lines of code. It's called MCP Toolboxโฆ
Google just open-sourced their MCP server for databases. Connect any database to any AI agent in 10 lines of code. It's called MCP Toolbox. What it handles: โ Connection pooling โ Authentication โ Query execution โ Tool generation โ OpenTelemetry tracing Supported databases: โโฆ
Claude Code is the most powerful AI today. (Especially with yesterday's Opus-4.6 release) Here's why it reached $1B ARR in 6 months and howโฆ
I just woke up Claude Code Agent Swarm on local Qwen3 Coder Next. No cloud. No Internet. No quota anxiety. No 'You've hit your limitโฆ
ComposioHQ/awesome-claude-skills: A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows - ComposioHQ/awesome-claude-skills
ChatGPT Containers can now run bash, pip/npm install packages, and download files
One of my favourite features of ChatGPT is its ability to write and execute code in a container. This feature launched as ChatGPT Code Interpreter nearly three years ago, was โฆ
MITโs new โrecursiveโ framework lets LLMs process 10 million tokens without context rot
While standard models suffer from context rot as data grows, MITโs new Recursive Language Model (RLM) framework treats prompts like code variables, unlocking infinite context without the retraining costs.
the MIT team reframes long-context reasoning as a systems problem. By letting models treat prompts as something they can inspect with code
Multimodal reinforcement learning with agentic verifier for AI agents - Microsoft Research
Argos improves multimodal RL by evaluating whether an agentโs reasoning aligns with what it observes over time. The approach reduces visual hallucinations and produces more reliable, data-efficient agents for real-world applications:
Argos is a verification framework for multimodal reinforcement learning
Argos evaluates how those behaviors were produced.
Zhipu AI Releases GLM-4.7-Flash: A 30B-A3B MoE Model for Efficient Local Coding and Agents - MarkTechPost
Zhipu AI Releases GLM-4.7-Flash: A 30B-A3B MoE (Mixture of Experts) Model for Efficient Local Coding and Agents
Claude Code costs up to $200 a month. Goose does the same thing for free.
Goose, Blockโs open-source AI coding agent, is emerging as a free alternative to Anthropicโs Claude Code, as developers weigh offline control, rate limits, and the rising cost of AI coding tools.
Add Reasoning Skills to Your LLM Apps | Aman Kharwal
In this article, Iโll walk you through a guided project to add reasoning skills to your LLM apps. Add Reasoning Skills to Your LLM Apps.
This dead simple prompt technique boosts accuracy on LLMs by up to 76%
The researchers found that simply repeating the input queryโliterally copying and pasting the prompt so it appears twice
look at the architectural limitations of the standard Transformer model.
Anthropic launches Cowork, a Claude Desktop agent that works in your files โ no coding required
Anthropicโs Cowork brings Claude Codeโstyle AI agents to the desktop, letting Claude access and manage local files and browse the webโboosting productivity while raising new security and trust risks.
First impressions of Claude Cowork, Anthropicโs general agent
New from Anthropic today is Claude Cowork, a โresearch previewโ that they describe as โClaude Code for the rest of your workโ. Itโs currently available only to Max subscribers ($100 โฆ
Sampling at negative temperature
Note: Looking at the equations above, if T<0T<0 then the sign of the exponent flips. That means that the states that were previously the least likely are now the most likely, and vice versa. As temperature approaches zero from the negative side, the model output will again be deterministic โ but this time, the least likely tokens will be output.
Looking at the equations above, if T<0T < 0T<0 then the sign of the exponent flips. That means that the states that were previously the least likely are now the most likely, and vice versa. As temperature approaches zero from the negative side, the model output will again be deterministic โ butโฆ
The Emperor Has No Clothes: How to Code Claude Code in 200 Lines of Code
The core of tools like Claude Code, Cursor, and Warp isn't magic. It's about 200 lines of straightforward Python. Let's build one from scratch.
GitHub Copilot
AI that builds with you
Why your LLM bill is exploding โ and how semantic caching can cut it by 73%
How Ralph Wiggum went from 'The Simpsons' to the biggest name in AI right now
Claude Code is about so much more than coding
Itโs a general-purpose AI agent. And itโs already a pretty good knowledge worker
Claude Wrote Me a 400-Commit RSS Reader App โ LessWrong
In the last few weeks, I've been playing around with the newest version of Claude Code, which wrote me a read-it-later service including RSS, email nโฆ
2025 LLM Year in Review from Andrej Karpathy
Training GPT-2 on a budget from Vishwanath Sangale
Impact Of On-Chip SRAM Size And Frequency On Energy Efficiency And Performance of LLM Inference (Uppsala Univ.)
A new technical paper titled โPrefill vs. Decode Bottlenecks: SRAM-Frequency Tradeoffs and the Memory-Bandwidth Ceilingโ was published by researchers at Uppsala University. Abstract โEnergy consumption dictates the cost and environmental impact of deploying Large Languageโฆ
Our simulation methodology combines OpenRAM for energy modeling, LLMCompass for latency simulation, and ScaleSIM for systolic array operational intensity.
Counter-intuitively, high compute frequency can reduce total energy by reducing execution time and consequently decreasing static energy consumption more than the resulting dynamic power increase
The Big LLM Architecture Comparison
From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design
Ollama Search
Search for models on Ollama.