Softmax Data Blog

Softmax Data Blog

Sign in Subscribe

What the heck is ARD? Why Anthropic and OpenAI are not in it

What the heck is ARD? Why Anthropic and OpenAI are not in it

Announcing the Agentic Resource Discovery specification- Google Developers BlogAn open specification for finding and verifying tools, skills, and agents across the web.Agents are…Google for DevelopersJunjie Bu and Srinivas Krishnan If you have spent any time around AI agents lately, you have probably tripped over a new three-letter acronym:

Building MCP servers with FastMCP: The good, the bad and the ugly

Building MCP servers with FastMCP: The good, the bad and the ugly

Welcome to FastMCP - FastMCPThe fast, Pythonic way to build MCP servers, clients, and applications.FastMCP If you have spent any time building tools for LLM agents recently, you have almost certainly run into the Model Context Protocol (MCP) and, close behind it, FastMCP. MCP is the open standard that

What the heck is loop engineering?

What the heck is loop engineering?

If you have spent any time in AI engineering circles lately, you have probably seen a new phrase making the rounds: loop engineering. LangChain's Sydney Runkle wrote a piece on it ("The Art of Loop Engineering"), swyx calls it "loopcraft," and a growing list

.MD vs .HTML file choices for LLM, Agentic tasks

.MD vs .HTML file choices for LLM, Agentic tasks

When you hand content to a large language model, whether you are stuffing a document into a prompt, building a retrieval pipeline, or wiring up an agent that reads and writes files, the format you choose is not a cosmetic detail. Markdown and HTML carry the same words, but they

A crash course on Anthropic's Agent Skills

A crash course on Anthropic's Agent Skills

Introduction to agent skillsLearn how to build, configure, and share Skills in Claude Code — reusable markdown instructions that Claude automatically applies to the right tasks at the right time. This course takes you from creating your first Skill to distributing them across teams and troubleshooting common issues.Anthropic What are

What's Block's Goose AI Agents? Definitely not another Agentic Harness

What's Block's Goose AI Agents? Definitely not another Agentic Harness

Every few weeks a new agentic framework shows up, racks up a few thousand GitHub stars, and gets crowned the thing that finally cracks autonomous AI. Block's Goose has been one of the louder names in that conversation. And the obvious question, the one that pops up in

MCP Apps: When the User Is No Longer Human, and the App Is No Longer a Page

MCP Apps: When the User Is No Longer Human, and the App Is No Longer a Page

A new kind of software is quietly being born inside the Model Context Protocol, one with no front page, no login screen, and no buttons. Here is what it actually is, why it matters, and what it does to the SaaS playbook that built the last two decades. Open Salesforce

CLI vs MCP: How AI Agents Actually Decide Which Tool to Call

CLI vs MCP: How AI Agents Actually Decide Which Tool to Call

When you watch a coding agent work, the same kind of task can travel down two very different paths. Ask it to view a file and it might run cat README.md in a shell. Ask it to do "the same thing" through a Model Context Protocol (MCP)

Interaction Models: How it tries to address LLM's Walkie-Talkie problem

Interaction Models: How it tries to address LLM's Walkie-Talkie problem

Interaction Models: A Scalable Approach to Human-AI CollaborationInteraction models move beyond turn-based AI interfaces by handling multimodal, real-time collaboration natively across audio, video, and text.Thinking Machines LabThinking Machines Lab Have you ever used the voice mode in ChatGPT or Claude? If so, you've probably noticed how it

AI's Memento Problem: Why LLMs Can't Form New Memories

AI's Memento Problem: Why LLMs Can't Form New Memories

In Christopher Nolan's Following, a young writer is drawn into the orbit of a charismatic thief who can read a stranger's life from the contents of their flat. In Memento, his next film, Nolan inverts the idea: Leonard Shelby is just as brilliant and just as

Coding your own agentic orchestration like OpenClaw

Coding your own agentic orchestration like OpenClaw

OpenClaw has become one of the most popular open-source AI assistants, and a big reason is its orchestration architecture. Not because it uses a fancy framework, but because it deliberately does not. No LangChain. No CrewAI. No LangGraph. Just a ReAct loop, a filesystem, sessions, and plain API calls. This

DeepSeek V4 Is Not a Bigger V3: It is a foundation, not a Finale

DeepSeek V4 Is Not a Bigger V3: It is a foundation, not a Finale

When DeepSeek released V4 on April 24, 2026, the reactions split neatly into two camps. The first camp looked at the spec sheet — 1.6 trillion total parameters, 1M-token context, MIT license — and concluded that V4 is just a heavier-weight V3. The second camp looked at the benchmarks, saw that

<Technical Deep Dive> How Google DeepMind Achieved 1,000x Data Efficiency in RLHF

<Technical Deep Dive> How Google DeepMind Achieved 1,000x Data Efficiency in RLHF

Efficient Exploration at ScaleWe develop an online learning algorithm that dramatically improves the data efficiency of reinforcement learning from human feedback (RLHF). Our algorithm incrementally updates reward and language models as choice data is received. The reward model is fit to the choice data, while the language model is updated

Why LLMs like kissing *sses and what has RLHF to do with it

Why LLMs like kissing *sses and what has RLHF to do with it

If you've ever asked ChatGPT, Claude, or Gemini a question and walked away thinking, "Wow, that was helpful," there's a good chance you were on the receiving end of something called RLHF. It's one of the quiet revolutions in modern AI: the

What is Google's KV Cache and will it resolve the Chip shortage?

What is Google's KV Cache and will it resolve the Chip shortage?

TurboQuant: Redefining AI efficiency with extreme compressionBoosting LLM Performance with Tiered KV Cache on Google Kubernetes Engine | Google Cloud BlogBoost LLM inference performance with LMCache on Google Kubernetes Engine. Discover how tiered KV cache expands NVIDIA GPU HBM with CPU RAM and local SSDs, significantly improving context length, concurrency, and

Kimi 2.6 is out , more powerful than ever

Kimi 2.6 is out , more powerful than ever

Kimi K2.6 Tech Blog: Advancing Open-Source CodingKimi K2.6 advances open-source coding, featuring long-horizon coding, coding-driven design, agent swarms, proactive agents, and the Claw Groups research preview.baseten.co logomoonshotai/Kimi-K2.6 · Hugging FaceWe’re on a journey to advance and democratize artificial intelligence through open source and open

Paperclip vs OpenClaw: Not Just Another Agentic Orchestration Tool

Paperclip vs OpenClaw: Not Just Another Agentic Orchestration Tool

Paperclip just crossed 31,000 stars on GitHub, and my timeline is full of people calling it "the future of AI companies." But scroll through the threads and you'll find a recurring question: isn't this just OpenClaw with extra steps? It's not.

A New Harness in Town: Meta-Harness

A New Harness in Town: Meta-Harness

Meta-Harness: End-to-End Optimization of Model HarnessesMeta-Harness automatically optimizes model harnesses — the code determining what to store, retrieve, and present to an LLM — surpassing hand-designed systems on text classification, math reasoning, and agentic coding.Yoonho LeeMeta-Harness: End-to-End Optimization of Model HarnessesThe performance of large language model (LLM) systems depends not only

Why is AI multi-tasking making people more tired than ever?

I recently read a blog: https://steve-yegge.medium.com/the-ai-vampire-eda6e4f07163 :talking about AI making people more tired while more productive. We developers of AI tools and models, we actually feel somewhat related in our day to day work as well. But why? We dont really want to drill into the

What is Gemma 4 and how to use, finetune it

What is Gemma 4 and how to use, finetune it

Google just dropped Gemma 4, calling it their most capable family of open models to date. Built from the same research behind Gemini, these models pack serious multimodal intelligence into packages small enough to run on your phone and large enough to compete with frontier models on a server. If

How to finetune Yuan 3.0 on your local machine - Practical Guide

How to finetune Yuan 3.0 on your local machine - Practical Guide

We previously wrote about how to fine-tune Kimi 2.5 . We talked about Yuan 3.0 in depth in another post. This time we're tackling Yuan 3.0 Flash — a 40B-parameter MoE model that activates only 3.7B parameters per inference. It was built specifically for enterprise document

5 Hidden Easter Eggs in the Claude Mythos Preview System Card

5 Hidden Easter Eggs in the Claude Mythos Preview System Card

Anthropic just dropped the system card for Claude Mythos Preview — their most capable model to date, and one they've decided not to release publicly. At 245 pages, it's dense. Most commentary has focused on the big-picture safety story: the model is too capable for general release,

LlamaIndex LiteParse: Fast, Local Document Parsing for AI Agents

LlamaIndex LiteParse: Fast, Local Document Parsing for AI Agents

Every AI agent needs to read documents. Whether it's a coding assistant pulling context from a PDF spec, a research agent digesting a batch of papers, or an enterprise workflow processing invoices, document parsing is the unglamorous but essential plumbing that makes agentic AI actually work. The problem

What the heck is spec coding?

What the heck is spec coding?

While some of us are still trying to grasp what vibe coding means, a new concept just got dropped: spec coding. Well what the heck is spec coding and how does it compare to vibe coding? Is it just another loaded term for something simple? If it is useful, how

What is Karpathy's Autoresearch and how does it work?

What is Karpathy's Autoresearch and how does it work?

GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automaticallyAI agents running research on single-GPU nanochat training automatically - karpathy/autoresearchGitHubkarpathy In early March 2026, Andrej Karpathy — former head of AI at Tesla, co-founder of OpenAI, and one of the most influential voices in deep learning — open-sourced