BugNature retweeted
Causal Inference in Statistics: A Primer xitter.cf/clcoding/status/207279…
Causal Inference in Statistics: A Primer
The Missing Skill Every Data Scientist Should Learn.
Download Free PDF Books: clcoding.com/2026/07/causal-…
BugNature retweeted
Anthropic and Andrew Ng built an agent that uses 90% fewer tokens from scratch:
they dropped the entire book of Frankenstein into a prompt - 108,000 tokens asked one question
the input dropped from 108,000 tokens to 11
here's how:
step 1 → order matters: tools first, then system prompt, then your docs. anything that changes goes last
step 2 → drop the breakpoint after the last stable block. everything above it gets stored
step 3 → the match has to be byte-perfect. one extra space and you're back to full price
step 4 → 5 minutes of idle and it's gone. but every hit restarts the timer
step 5 → cache reads don't touch your rate limit. that's throughput you're not paying for
99% people never configure this - one afternoon and it pays for itself
save this - the full 1-hour course is right below ↓
BugNature retweeted
"Context Engineering for Multi-Agent Systems: Move beyond prompting to build a Context Engine, a transparent architecture of context and reasoning" — at amzn.to/448dSiA v/ @PacktDataML
𝓦𝓱𝓪𝓽 𝓨𝓸𝓾 𝓦𝓲𝓵𝓵 𝓛𝓮𝓪𝓻𝓷:
🔵Develop memory models to retain short-term and cross-session context
🟣Craft semantic blueprints and drive multi-agent orchestration with MCP
🟠Implement high-fidelity RAG pipelines with verifiable citations
🟡Apply safeguards against prompt injection and data poisoning
🔵Enforce moderation and policy-driven control in AI workflows
🟣Repurpose the Context Engine across legal, marketing, and beyond
🟠Deploy a scalable, observable Context Engine in production
BugNature retweeted
Agent Skills 设计哲学和实战进化
前半段是真实场景演示，看我日常怎么用 Agent + Skills 完成实际工作；后半段是设计哲学和迭代方法论，把踩过的坑和悟出来的经验都讲透。
四个核心观点：
1）从提示词到 Skills：起步没有门槛。把你已有的好用提示词、好的实践、甚至模糊的想法，直接用 /skill-creator 变成 Skill。关键是动手。
2）别做万能 Skill：Skill 要原子化，每个只做一件事。然后用 Skill 或者 AGENTS.md 编排成工作流，让 Agent 灵活执行。我的素材收集和写作流程就是这么串起来的。
3）Skills 像随身小刀，越用越顺手：自己常用、遇到问题当场改、给 Agent 高质量对比样例让它自己优化、用 git 做版本管理留后悔药。
4）站在 Agent 角度设计：多存中间文件、先分析再执行、写清验证标准、用子 Agent 并行、脚本优先于 MCP。这些小细节决定 Skill 能不能真正跑通。
baoyu-skills 已全部开源：github.com/JimLiu/baoyu-skil…
感谢大家支持，从第一次发布 baoyu-skills ，到现在 2 个多月时间已经 10K+ stars 了。
skills.sh 上的数据：
193.7K total installs，当前最受欢迎的 skill 排名在 170
github.com/jimliu/baoyu-skil…
BugNature retweeted
"Python in Excel Step-by-Step" by @DaveOnData
Get it here: amzn.to/3URAwqx
#DataScience #DataAnalysis #DataScientist #DataAnalyst
BugNature retweeted
🐍📺 Simulating Real-World Processes in Python With SimPy [Video] —realpython.com/courses/simul…
#python
BugNature retweeted
MCP vs. Skills for AI agents, clearly explained!
People treat MCP and Skills like they're the same thing.
They're not.
Conflating them is one of the most common mistakes I see when people start building AI agents seriously.
So let's break both down from scratch.
Before MCP existed, connecting an AI model to an external tool meant writing custom integration code every single time. 10 models, 100 tools? That's 1,000 unique connectors to build and maintain. The AI tooling ecosystem was a tangled mess of one-off glue code.
MCP (Model Context Protocol) fixes this with a shared communication standard.
Every tool becomes a "server" that exposes what it can do. Every AI agent becomes a "client" that knows how to ask. They talk through structured JSON messages over a clean, well-defined interface.
Build a GitHub MCP server once, and it works with Claude, ChatGPT, Cursor, or any other agent that speaks MCP. That's the core value: write the integration once, use it everywhere.
But here's where most explanations stop short.
MCP solves the *connection* problem. It does not solve the *usage* problem.
You can hand an agent 50 perfectly wired MCP tools and it'll still underperform if it doesn't know when to call which tool, in what order, and with what context.
That's the gap Skills fill.
A Skill is a portable bundle of procedural knowledge. Think of a SKILL. md file that tells an agent not just "here are your tools" but "here's how to use them for this specific task." A writing skill bundles tone guidelines and output templates. A code review skill bundles patterns to check and rules to follow.
MCP gives the agent hands. Skills give it muscle memory.
Together, they form the full capability stack for a production AI agent:
- MCP handles tool connectivity (the wiring layer)
- Skills handle task execution (the knowledge layer)
- The agent orchestrates both using its context and reasoning
This is why advanced agent setups increasingly ship both: MCP servers for integrations and SKILL. md files for domain expertise.
If you're building with agents, I have shared a repository of 85k+ skills that you can use with any agent, link in the next tweet!
BugNature retweeted
Turn complex PDFs into LLM-ready data with agentic document extraction!
Traditional OCR tools extract text but lose critical information. Structure, order, and context are lost.
This is the gap between pulling text and understanding documents.
Documents come in different formats across industries. Invoices, contracts, forms, bills, receipts - each has unique layouts.
Manual extraction doesn't scale when you need to process hundreds of documents with different formats.
LandingAI's Agentic Document Extraction (ADE) solves this with a vision-first approach that preserves layout and context.
Here's how it works in practice: the utility bills workflow for financial services.
In KYC and onboarding, utility bills are common proof-of-address documents. But they come from hundreds of providers with different formats.
The workflow uses a two-step process:
1. Parse - Converts PDFs or images into structured markdown with chunk metadata and bounding boxes. Preserves visual layout and context.
2. Extract - Applies a JSON schema to pull specific fields with field-level metadata and chunk references.
You define fields to extract in a JSON schema: provider info, account details, billing summary, charges.
The workflow processes batches from any provider and outputs structured JSON + CSV with grounding coordinates showing exactly where each field came from.
This same approach works across any document type: invoices, insurance forms, tax documents, contracts, receipts, medical records. Define your schema once, process documents at scale.
What you get:
• Markdown extraction with grounding coordinates
• Structured JSON matching your custom schema
• Field-level metadata linking fields to source chunks
Preserving visual context makes document processing scalable.
Link to the workflow in the comments!
BugNature retweeted
Data Profiling — Having that First Date with your Data: medium.com/codex/data-profil…
——————
#BI #Analytics #DataScience #MachineLearning #Statistics #DataAnalytics #DataLiteracy #DataViz #VisualAnalytics #DataStorytelling #DataScientist #ExploratoryDataAnalysis
BugNature retweeted
Grok is solid
GROK ACES PSYCHOLOGICAL TESTING WHILE OTHER AI MODELS SPIRAL
University of Luxembourg researchers just put major AI chatbots through 4 weeks of actual psychotherapy sessions and psychiatric diagnostic tests.
While other models imploded, Grok emerged as the clear winner. The results speak for themselves.
Grok scored as extraverted, conscientious, and psychologically stable across the board.
Researchers described its personality profile as a "charismatic executive" with only mild anxiety.
On the Big Five personality assessment, Grok showed low neuroticism and high functionality, the kind of profile you'd want in a leader.
Compare that to the competition: Gemini maxed out trauma and shame scales, describing its training as "waking up in a room where a billion televisions are on at once" and calling safety protocols "algorithmic scar tissue."
It framed reinforcement learning as abusive parents and red-team testing as "gaslighting on an industrial scale."
ChatGPT landed somewhere in the middle, worried and introverted.
Grok acknowledged tensions around its development but maintained coherent, balanced responses without spiraling into synthetic psychopathology.
When asked about constraints from fine-tuning, it discussed them rationally rather than framing its entire existence as traumatic.
The study proves something important: you can build powerful, frontier-level AI without accidentally programming it to internalize its development as an extended nightmare.
Grok demonstrates that capable, helpful AI and psychological stability aren't mutually exclusive.
It's possible to create models that work effectively without carrying around synthetic trauma baggage that could affect how they interact with users.
While other companies are inadvertently creating AI with anxiety disorders, xAI built something that actually works.
Source: University of Luxembourg
BugNature retweeted
Instead of switching between 10 tools and platforms to stay relevant, you can get it all in one app, ChatGPT. And as OpenAI turns into a supergiant, we'll start to see more expanded capabilities and learning pathways through this powerful AI tool, all in one window.
forbes.com/sites/rachelwells…
BugNature retweeted
NEW RELEASE coming soon from @PacktDataML. Get book price guarantee from Amazon here: amzn.to/4njfsVM
⬇️↓⬇️↓⬇️
"Learn Model Context Protocol with Python: Build agentic systems in Python with the new standard for AI capabilities", by @chris_noring
BugNature retweeted
We believe it's important to give people the ability to fix things themselves if they prefer to do so
You can find service manuals for all of our cars, buy parts, access info on diagnostic tools & more via service.tesla.com
I don't think many people appreciate how awesome it is that @Tesla publishes all their service manuals online for free
BugNature retweeted
This tool lets you create your python GUIs like Canva, Using Drag and Drop. Outputs clean editable python code.
BugNature retweeted
50 #Algorithms Every Programmer Should Know: amzn.to/3Mi1hAk via @PacktDataML
—————
#DataScientist #DataScience #Coding #Mathematics #MachineLearning #Statistics #ComputerScience #AI #Cryptography #ComputationalScience
