# modern ai (blogs) — RSS Amplifier

Recent posts from the 5 feeds in the RSS Amplifier directory that cover modern ai.

Page: <https://rssamplifier.com/topics/modern-ai/blogs>  
Feed: <https://rssamplifier.com/topics/modern-ai/blogs.md>

---

## [How LLM Guardrails Work, ColBERT and InstructGPT Decoded](https://outcomeschool.substack.com/p/how-llm-guardrails-work-colbert-and)

_2026-08-15 · Outcome School · Outcome School Newsletter_

Safety gates, late-interaction retrieval, and the RLHF recipe that led to ChatGPT

## [Building AI-Native Organizations](https://hosanagar.substack.com/p/building-ai-native-organizations)

_2026-08-14 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

Marketing as a case study for how to make your function more AI native

## [Bill Watterson's approach to deadlines](http://senthil.learntosolveit.com/posts/2026/08/13/bill-wattersons-approach-to-deadlines.html)

_2026-08-13 · Senthil Kumaran · Senthil Kumaran_

I noted down a discipline practice that one of my favorite creators used. I had also seen this practice with a successful student, Yesh Dattareya, at the OMSCS. His (Bill Watterson's) approach to deadlines was to stay well ahead of them. When you’re faced with a due date (as he told Lee Nordling in Your Career in Comics ) “there’s no quality control. It’s just garbage in, garbage out.” This was…

## [The Norway Problem in Yaml](http://senthil.learntosolveit.com/posts/2026/08/10/the-norway-problem-in-yaml.html)

_2026-08-10 · Senthil Kumaran · Senthil Kumaran_

Norway's ISO country code is NO. Under the YAML 1.1 spec, unquoted no (case-insensitive, along with yes, on, off, y, n, true, false) is treated as a boolean and not a string. You can see the problem here. ~ cat test . yaml countries : - NO - SE - NL - IN - US - SG ~ python \>\>\> import yaml \>\>\> with open ( "test.yaml" ) as f : ... data = yaml . safe\_load ( f ) ... \>\>\> print ( data ) { 'countries' :…

## [AI Model Can Be Hijacked With Plain English](https://outcomeschool.substack.com/p/ai-model-can-be-hijacked-with-plain)

_2026-08-08 · Outcome School · Outcome School Newsletter_

The top LLM attack, plus deployment, Transformers, Generative AI, and Precision vs Recall

## [Towards Self-Repairing and Repeatable AI Systems](https://iaee.substack.com/p/towards-self-repairing-and-repeatable)

_2026-08-05 · Daniel Warfield · Intuitively and Exhaustively Explained_

Recent Progress in the Agent Harnesses Standard

## [What Are Embeddings, Agent Skills, MCP, and OKF?](https://outcomeschool.substack.com/p/what-are-embeddings-agent-skills)

_2026-08-01 · Outcome School · Outcome School Newsletter_

Plus how fine-tuning turns a general model into a specialist

## [Infrastructure on Google Cloud—Intuitively and Exhaustively Explained](https://iaee.substack.com/p/infrastructure-on-google-cloudintuitively)

_2026-07-28 · Daniel Warfield · Intuitively and Exhaustively Explained_

A high-level breakdown of the major components of cloud architecture

## [AI versus the MBA](https://hosanagar.substack.com/p/ai-versus-the-mba)

_2026-07-26 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

What skills will entry-level knowledge work require and how should MBAs and undergrads be trained?

## [How Cursor, Claude Code, and llama.cpp Actually Work](https://outcomeschool.substack.com/p/how-cursor-claude-code-and-llamacpp)

_2026-07-25 · Outcome School · Outcome School Newsletter_

Plus Semantic Search, context compaction, and model quantization, explained simply

## [8.1% APY Plus Free Stock (Sponsored)](https://crawlproof.com/a/ZamGdAGf0JgF)

_2026-07-25 · **Sponsored**_

Claim 8.1% APY and up to $1,030 in SK hynix and Nvidia stock.

## [How Prefill, Decode, HyDE, and Hybrid Search Work](https://outcomeschool.substack.com/p/how-prefill-decode-hyde-and-hybrid)

_2026-07-11 · Outcome School · Outcome School Newsletter_

Plus Semantic Caching, PyTorch, Prompt Chaining, and Chain-of-Thought, explained simply

## [Identity matters](http://senthil.learntosolveit.com/posts/2026/07/05/identity-matters.html)

_2026-07-05 · Senthil Kumaran · Senthil Kumaran_

Identity matters. To do good work, you need a strong sense of how to be effective, models for valuable work. Most often, you acquire these from the communities you belong to. On Developing Creative Identity by Michael Nielsen

## [On Buddhism](http://senthil.learntosolveit.com/posts/2026/07/05/on-buddhism.html)

_2026-07-05 · Senthil Kumaran · Senthil Kumaran_

In Buddhism, there are 14 unanswerable questions about the big-picture nature of the cosmos: how did it start, how old it is, and so on. The Buddha tells us not to worry about these big picture questions, that what matters is addressing suffering. To illustrate, he tells a parable in which a man struck by a poisoned arrow refuses to have it removed, until he knows who shot it, what kind of arrow…

## [How LangChain, LangGraph, and SGLang Actually Work](https://outcomeschool.substack.com/p/how-langchain-langgraph-and-sglang)

_2026-07-04 · Outcome School · Outcome School Newsletter_

Plus ANN search, Google TPUs, and GPUs for deep learning, decoded

## [The Documentation is the Code](https://iaee.substack.com/p/the-documentation-is-the-code)

_2026-06-30 · Daniel Warfield · Intuitively and Exhaustively Explained_

A great inversion in software development

## [Agent Harnesses with Claude — Intuitively and Exhaustively Explained](https://iaee.substack.com/p/agent-harnesses-with-claude-intuitively)

_2026-06-27 · Daniel Warfield · Intuitively and Exhaustively Explained_

Towards faster, less expensive, more maintainable, and more consistent agents

## [How Computer-Use Agents, Embeddings, and DLMs Work](https://outcomeschool.substack.com/p/how-computer-use-agents-embeddings)

_2026-06-27 · Outcome School · Outcome School Newsletter_

Plus an Embedding Cache deep-dive and the Sakana Fugu report, decoded

## [vLLM, Function Calling, and World Models explained](https://outcomeschool.substack.com/p/vllm-function-calling-and-world-models)

_2026-06-20 · Outcome School · Outcome School Newsletter_

How vLLM, Function Calling, and World Models actually work

## [XKCD diagram creator with cmx.js](http://senthil.learntosolveit.com/posts/2026/06/17/xkcd-diagram-creator-with-cmxjs.html)

_2026-06-17 · Senthil Kumaran · Senthil Kumaran_

I could bring back the an old utility I used to like. An XKCD style diagram creator. I lives here now. https://orsenthil.github.io/cmx.js/ Original Author is Antonin Hildebrand and here is his repo https://github.com/darwin/cmx.js/. There is a great post by a David Walsh explaining it https://davidwalsh.name/cmx-js Now that is up in the web, I think, a good idea will be the embed a local web model…

## [Besides, Michelangelo wasn't Michelangelo until](http://senthil.learntosolveit.com/posts/2026/06/17/besides-michelangelo-wasnt-michelangelo-until.html)

_2026-06-17 · Senthil Kumaran · Senthil Kumaran_

## [Licensed Dispensaries, Pay with Crypto (Sponsored)](https://crawlproof.com/a/MVMpHbtFnpWW)

_2026-06-17 · **Sponsored**_

Search verified licensed dispensaries and pay with Bitcoin, Lightning, or stablecoins.

## [Agent Harnesses — Intuitively and Exhaustively Explained](https://iaee.substack.com/p/agent-harnesses-intuitively-and-exhaustively)

_2026-06-16 · Daniel Warfield · Intuitively and Exhaustively Explained_

A new standard for modern AI agent development

## [LiteParse](http://senthil.learntosolveit.com/posts/2026/06/16/liteparse.html)

_2026-06-16 · Senthil Kumaran · Senthil Kumaran_

Inspired from Simon Willison's post, I created fork of liteparse project and deployed it - https://orsenthil.github.io/liteparse/ It is wonderful to see browsers and models running in browser, capable of parsing PDFS, and doing OCR without sending the data to the cloud or any other service. The capabilities are just mind blowing.

## [How Prompt Caching, RAG, and GGUF actually work](https://outcomeschool.substack.com/p/how-prompt-caching-rag-and-gguf-actually)

_2026-06-13 · Outcome School · Outcome School Newsletter_

6 ideas that power AI search, RAG, and local models

## [linkding safari extension](http://senthil.learntosolveit.com/posts/2026/06/11/linkding-safari-extension.html)

_2026-06-12 · Senthil Kumaran · Senthil Kumaran_

I like the linkding link manager. I realized the extension is provided only for Chrome and Firefox, as publishing for Safari and Mac will require the developer to pay yearly developer fees. The best way is to build one yourself. Use this orsenthil/safari-linkding-extension to build the linkding extension for your safari on mac.

## [AI Agents Learning Roadmap with Resources](https://outcomeschool.substack.com/p/ai-agents-learning-roadmap-with-resources)

_2026-06-06 · Outcome School · Outcome School Newsletter_

Everything about AI Agents

## [The AI Labor Debate Is Asking the Wrong Question: Citrini Doomsday Scenario Revisited](https://hosanagar.substack.com/p/the-ai-labor-debate-is-asking-the)

_2026-05-13 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

A viral AI doomsday scenario doesn't account for non-technological constraints in AI deployment

## [Agent Skills — Intuitively and Exhaustively Explained](https://iaee.substack.com/p/agent-skills-intuitively-and-exhaustively)

_2026-05-12 · Daniel Warfield · Intuitively and Exhaustively Explained_

Defining Reusable Plans for Agentic Systems

## [Why LLMs Make Learning to Code More Important, Not Less](http://senthil.learntosolveit.com/posts/2026/05/10/why-llms-make-learning-to-code-more-important-not-less.html)

_2026-05-10 · Senthil Kumaran · Senthil Kumaran_

This is the transcript of my talk at OMSCS Conference 2026 Hello, everyone. I'm Senthil Kumaran, a software developer at Uber. I've been programming for more than 20 years. I completed my OMSCS specialization in 2019 with specializations related to Computer Vision and Computational Systems. I had taken twelve courses in all, and I've stayed close to the program ever since. This is my first…

## [Annotated History of Modern AI and Deep Learning](http://senthil.learntosolveit.com/posts/2026/05/09/annotated-history-of-modern-ai-and-deep-learning.html)

_2026-05-09 · Senthil Kumaran · Senthil Kumaran_

This is a wonderful resource on the History of Modern AI and Deep Learning by Jürgen Schmidhuber . It opens statement with Machine learning (ML) is the science of credit assignment. It takes the technical term of "Credit Assignment" and overlays it with the human approach of assigning credits to ideas shared by predecessors. It reminds us that we are all standing on the shoulders of the giants . I…

## [Developing Native Android Applications in Kotlin — Intuitively and Exhaustively Explained](https://iaee.substack.com/p/developing-native-android-applications)

_2026-04-25 · Daniel Warfield · Intuitively and Exhaustively Explained_

A comprehensive guide to making native Android apps

## [Finnish Seedboxes — Up to 20Gbps (Sponsored)](https://crawlproof.com/a/YMYecJX5bXxc)

_2026-04-25 · **Sponsored**_

Private Finnish seedboxes with 1–20Gbps speeds, RAID storage and 14‑day refund

## [Agile Project Management — Intuitively and Exhaustively Explained](https://iaee.substack.com/p/agile-project-management-intuitively)

_2026-03-09 · Daniel Warfield · Intuitively and Exhaustively Explained_

How Teams Get Things Done

## [Combinatorics in Probability — Intuitively and Exhaustively Explained](https://iaee.substack.com/p/combinatorics-in-probability-intuitively)

_2026-02-05 · Daniel Warfield · Intuitively and Exhaustively Explained_

Part 1 of an Introduction to Probability

## [When AI Becomes the Customer](https://hosanagar.substack.com/p/when-ai-becomes-the-customer)

_2026-01-28 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

What Walmart’s bet on agentic commerce reveals about the questions facing retail

## [Another Year Around the Sun](https://hosanagar.substack.com/p/another-year-around-the-sun)

_2026-01-02 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

On travel, recovery, and working with more ease and freedom

## [Don’t Be Distracted In 2026](https://iaee.substack.com/p/dont-be-distracted-in-2026)

_2026-01-01 · Daniel Warfield · Intuitively and Exhaustively Explained_

Tools to be Happy In a Digital World

## [AI is Deskilling you. Here’s How to prevent It](https://hosanagar.substack.com/p/ai-is-deskilling-you-heres-how-to)

_2025-12-14 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

Why the effort we avoid is often the expertise we lose

## [Ep 8: Can AI be Conscious? Prof Anil Seth on Sentient Machines](https://hosanagar.substack.com/p/can-ai-be-conscious-prof-anil-seth)

_2025-09-01 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

Why the illusion of consciousness could be dangerous

[Listen](https://api.substack.com/feed/podcast/172516391/6a9c991dc0fb36c928b116e93dc6f067.mp3)

## [Ep 7: The AI Stack: Data, Agents, Organizations, and RoI](https://hosanagar.substack.com/p/ep-7-the-ai-stack-data-agents-organizations)

_2025-08-20 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

You can see the Gen AI age everywhere—except in the productivity stats.

[Listen](https://api.substack.com/feed/podcast/171491166/caff5a3e7c0fdb5986939a1dc2404431.mp3)

## [Ep 6: With AI, Everyone Will Be a Manager of 50 AI Agents](https://hosanagar.substack.com/p/ep-6-with-ai-everyone-will-be-a-manager)

_2025-08-06 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

Watch now | Grammarly's new CEO on the agentic future of work and building company rituals

[Listen](https://api.substack.com/feed/podcast/170139429/b417d502e9a4c89fc9af346fb1f90ffc.mp3)

## [Hey AI, buy my product: How LLMs are rewriting the customer journey](https://hosanagar.substack.com/p/hi-ai-buy-my-product-how-llms-are)

_2025-07-30 · Kartik Hosanagar · Creative Intelligence | Kartik Hosanagar_

As search engines give way to answer engines, businesses are not fully prepared to start persuading large language models—not just people.

## [A Catalogue of AI Research Idea Generators](https://deliprao.com/2024/09/a-catalogue-of-ai-research-idea-generators/)

_2024-09-04 · Delip Rao · Delip Rao_

I am offering a preliminary catalog of AI research idea generators distilled from at least a thousand AI research papers I have read, skimmed, or glanced at during my career. I have not seen this anywhere else. Each of these is a tried and tested formula/recipe for generating AI research ideas.

