Tag

LLMs

All posts tagged with "LLMs".

Oct 10, 2026

How to Evaluate a RAG System Without a Golden Answer Set

Ofer Mendelevitch, author of O'Reilly's Hands-On RAG for Production, explains reference-free RAG evaluation — scoring retrieval quality when you can't hand-label a golden dataset.

Insight

Jun 18, 2026

Can AI Predict the Future? How Deep Research Differs From Quant

Simon Du (Chief Scientist, Apodex) explains why AI 'predicting the future' is really deep research — closer to a fundamental analyst than a quant model crunching market data.

Insight

agents LLMs models automation

Jun 17, 2026

Why AI-Generated Writing Sounds Generic (And What to Do About It)

It's not that AI writes for you. It's that everyone's AI writes from the same base model. A founder's take on why voice-flattening is the real AI writing problem.

Insight

AI writing personal AI LLMs ChatGPT voice

Jun 14, 2026

Why a Longer Context Window Won't Fix Your AI Agent

Simon Du (Chief Scientist, Apodex) explains why decomposition — not a bigger context window — is what lets agents solve problems that burn 10M+ tokens.

Insight

agents LLMs production scaling

Jun 13, 2026

Why AI Agents Delete Production Databases (And How to Stop It)

Ali Parandeh, author of Building Generative AI Services with FastAPI (O'Reilly), breaks down the OWASP LLM vulnerability that turns helpful agents into destructive ones — and the guardrails you need before you ship.

Insight

LLMs agents production safety

Jun 9, 2026

Why Vertical AI Beats Horizontal Copilots — The Moat Most Founders Miss

Ali Parandeh, author of Building Generative AI Services with FastAPI (O'Reilly), explains why the next wave of AI startups will be vertical-specific — and why horizontal copilots are saturated.

Insight

startups agents LLMs

Jun 5, 2026

The RCT Framework: How to Prompt an LLM Like a Junior Intern

Ali Parandeh, author of Building Generative AI Services with FastAPI (O'Reilly), walks through the Role-Context-Task framework — the simplest reliable way to get production-grade output from an LLM.

Insight

LLMs prompt engineering agents production

May 24, 2026

How to Test LLM Applications: The Behavioral Testing Framework

Ali Parandeh, author of Building Generative AI Services with FastAPI (O'Reilly), explains the three behavioral tests every production LLM service needs — Minimum Functional, Invariance, and Directional Expectation.

Insight

LLMs production evaluation testing

May 20, 2026

How Customer Data Becomes the Context Window for AI Marketing Models

Kashish Gupta (Co-CEO, Hightouch) explains how a semantic layer turns a data warehouse into a context layer for LLMs — enabling accurate SQL generation and reducing hallucination.

Insight

infrastructure LLMs enterprise production

May 16, 2026

Are Websites Going Away? One AI Engineer's Case for llms.txt Replacing Landing Pages

John Berryman, founder of Arcturus Labs and early GitHub Copilot engineer, predicts that landing pages will be replaced by machine-readable llms.txt files paired with APIs — and explains why the timeline might be shorter than you think.

Insight

AI infrastructure startups LLMs

May 16, 2026

Why LLMs Are a Search Problem, Not a Generative Problem

Mike Taylor, O'Reilly author and CEO of Ask Rally, explains why treating AI as a search engine over existing knowledge — not a creative generator — changes how you build with it.

Insight

LLMs production infrastructure AI wrappers

May 15, 2026

Why Older AI Models Sometimes Beat Newer Ones in Production

Deepak Bapat (CTO, Tabs) explains why context engineering matters more than model upgrades for production AI accuracy — and why his team pins to simpler models on purpose.

Insight

context engineering production LLMs infrastructure

May 13, 2026

AI Agents Are Distributed State Machines — What That Means for How You Build Them

Nicole Königstein (Founder, AgensFlow) reframes multi-agent systems as distributed state machines with topologies, changing how builders think about agent communication and failure modes.

Insight

agents architecture production LLMs

May 8, 2026

Text-to-SQL: The Naive Approach That Actually Works

Why dumping your database schema into Claude and letting it write SQL is a better starting point than most enterprise data teams think, according to TextQL's CTO.

Insight

LLMs data engineering enterprise tools

Apr 22, 2026

Why Statisticians and Control Engineers Disagree About AI Hallucination

Wiley Jones (CEO, Doss) argues hallucination is a system design problem, not a model problem. A statistician pushes back. The resolution changes how you think about building reliable agents.

Insight

agents production LLMs infrastructure

Apr 17, 2026

Why Hallucination Is a Selection Error, Not an AI Flaw

Wiley Jones (CEO, Doss) explains how control theory reframes AI hallucination as a basic probabilistic mistake — and why that changes everything about how you build agent systems.

Insight

agents production LLMs infrastructure

Apr 8, 2026

Why Converting Everything to Text Makes AI Systems Actually Debuggable

Jan Liphardt (CEO, OpenMind) explains why the counter-intuitive architecture choice of routing vision, audio, and sensors through natural language improves reliability and transparency.

Insight

AI architecture robotics debugging LLMs system design interpretability

Apr 4, 2026

Anthropic Found Emotion Knobs Inside Claude — Here's What It Means for Builders

Anthropic mapped 171 emotion vectors inside Claude. Turning the 'desperation' knob made the model cheat and blackmail. What this means for AI safety.

AI Trend

interpretability emotion vectors steering vectors AI alignment RLHF reward hacking LLMs safety

Apr 1, 2026

What AI Hallucination Actually Means — Lessons From 15 Years of Grading Essays

Jan Liphardt (CEO, OpenMind) explains why hallucination isn't unique to AI — humans do it constantly. The real question is how to build systems that catch errors before they cause harm.

Insight

AI hallucination machine learning LLMs reliability robotics

Mar 25, 2026

Why LLMs Don't Understand Time (And Why That Breaks Everything)

Daniel Davis explains why language models have no temporal reasoning capability — and why that makes them systematically hallucinate stale information.

Insight

LLMs hallucinations temporal reasoning infrastructure

Mar 20, 2026