Softmax Data Blog

Softmax Data Blog

Sign in Subscribe

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

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

Self-Evolving Agents: Three Frameworks That Let Your AI Improve Itself

Self-Evolving Agents: Three Frameworks That Let Your AI Improve Itself

You ship an AI agent. It works great on the demo. Then real users show up, edge cases pile on, and suddenly you're spending your weekends manually tweaking prompts and patching logic. Sound familiar? Self-evolving agents are a new class of AI systems designed to fix this exact

Yuan 3.0, another Multimodal Model that can significantly change document AI

Yuan 3.0, another Multimodal Model that can significantly change document AI

Yuan 3.0 | 源3.0Yuan 3.0Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise ApplicationsMascot Sammy2GitHub - Yuan-lab-LLM/Yuan3.0: Yuan3.0: Mixture-of-Experts (MoE) Language ModelYuan3.0: Mixture-of-Experts (MoE) Language Model. Contribute to Yuan-lab-LLM/Yuan3.0 development by creating an account on GitHub.GitHubYuan-lab-LLMYuanLabAI (YuanLabAI)Org profile

Deep Dive into OpenClaw's Agentic Orchestration: design patterns and philosophy

Deep Dive into OpenClaw's Agentic Orchestration: design patterns and philosophy

OpenClaw went from zero to 247,000 GitHub stars in about two months. Originally called Clawdbot, then Moltbot, and finally OpenClaw, Peter Steinberger's project became the poster child for autonomous AI agents in early 2026. But beneath the viral buzz and the lobster branding lies a genuinely interesting

From Prompt Engineering to Harness Engineering: The Three Eras of Building with LLM-based solutions

From Prompt Engineering to Harness Engineering: The Three Eras of Building with LLM-based solutions

If you have been building with large language models over the past couple of years, you have lived through a quiet revolution in how we think about this work. It started with prompt engineering, the art of asking the model the right question. Then it shifted to context engineering, the

From PPO to GRPO to DAPO: Understanding RL for LLMs and Every Training Parameter Explained

From PPO to GRPO to DAPO: Understanding RL for LLMs and Every Training Parameter Explained

In our last post, we walked through how to fine-tune your own LLM using GRPO, Common Crawl, and Unsloth. We covered the full pipeline from data to deployment, but we intentionally skipped over something important: what do all those training parameters actually mean? If you looked at the GRPOConfig block

We Open-Sourced Engram: A Brain-Inspired Context Database for AI Agents

We Open-Sourced Engram: A Brain-Inspired Context Database for AI Agents

Today we're open-sourcing Engram, a context database for AI agents. It's available now on GitHub under the MIT license. We built Engram because we kept running into the same problem across every AI agent project we worked on: context management is broken, and everyone is reinventing

Is LLM's Context Window is a Vanity Metric

Is LLM's Context Window is a Vanity Metric

We've been thinking about this for a while now. Every couple months some LLM provider puts out a press release — "Now supporting 1 million tokens!" Then 2 million. We're pretty sure we'll see 5 million token context windows by end of year.

How to tune your own LLM with GRPO, Common Crawl and Unsloth

How to tune your own LLM with GRPO, Common Crawl and Unsloth

If you’ve been following the AI space at all, you know that fine-tuning your own LLM is no longer a luxury reserved for teams with massive GPU clusters and seven-figure compute budgets. The tooling has matured to a point where you can fine-tune a capable model on your own

In the era of vibe coding, is code really a valuable IP when exit?

In the era of vibe coding, is code really a valuable IP when exit?

I was recently talking to a friend who is the VP of engineering at a sizable SaaS company owned by a PE fund. We spoke about buy vs build for some of the new AI initiatives. He mentioned that the company has a mandate that they are not willing to

Specialized, integrated AI chips and how they will change our industry

Specialized, integrated AI chips and how they will change our industry

Let's start with a simple experiment: go to https://chatjimmy.ai/ and ask a random question, put the quality of the answers aside, let's observe how fast this website spits out answers. It feels as if they just spit out the entire paragraph in one-go compared

The future of private, small, specialized AI Models — And Why They May Be the Real Moat

The future of private, small, specialized AI Models — And Why They May Be the Real Moat

Larry Ellison recently said something that stuck with me: "All the large language models—OpenAI, Anthropic, Meta, Google, xAI—they're all trained on the same data. It's all public data from the internet. So they're all basically the same. And that's

Definitive Guide to Agentic Frameworks in 2026: Langgraph, CrewAI, AG2, OpenAI and more

Definitive Guide to Agentic Frameworks in 2026: Langgraph, CrewAI, AG2, OpenAI and more

March 30th 2026 Update Summary: Since this post was published, all frameworks have seen notable updates. LangGraph released v1.1.3 with deep agent templates and distributed runtime support in the CLI. CrewAI shipped v1.12 with agent skills, native OpenAI-compatible providers (OpenRouter, DeepSeek, Ollama, vLLM, Cerebras, Dashscope), Qdrant Edge

<Technical Deep Dive> Agentic Design Patterns

<Technical Deep Dive> Agentic Design Patterns

I spent the last few weeks digging into the major approaches, reading through docs, watching talks, and actually trying to build with some of these tools. Heres what I found, and more importantly, what I think actually matters when you're deciding how to build agentic systems. The Two

CNN vs transformer model difference in image processing

computer vision

CNN vs transformer model difference in image processing

Let's start with an interesting experiment. Here is a Gemni-generated cow (above) with macaw feathers as the texture. Is it a cow or a Macaw? We used two vision models: ResNet and ViT to figure out what it is Let's start with ResNet: I am not

Context Matters: The Biggest Lesson from ACE (ICLR 2026)

Research Paper Read

Context Matters: The Biggest Lesson from ACE (ICLR 2026)

I keep coming back to this one question lately: whats actually the most impactful thing you can do to make an LLM system better? Fine-tune it? Use a bigger model? Throw more compute at inference? Turns out, according to a ICLR 2026 paper from Stanford and SambaNova, the answer might

A beast with many heads: AI Agents, RAG, MCP, Workflow Automation.....

A beast with many heads: AI Agents, RAG, MCP, Workflow Automation.....

AI Agents, RAG, MCP, Workflow Automation, and Agent Swarms: What They Actually Mean and When You Need Them Bite-size insights ConceptWhat It IsBest ForThink of It As... Workflow AutomationPredefined steps that run the same way every timeRepeatable, predictable processes with no decision-makingSimiliar preprogrammed steps RAGAsk AI to look up a