Prompt Engineering

Oct 2

On October 2, 2026, Andrej Karpathy posted a short ladder for understanding what language models write: controlled-language text, then diagrams, then HTML pages, then bespoke explainer videos. Here is what each rung means, the exact prompts to try, and where the advice breaks down.

Sep 24

Sep 21

Sep 19

Security researcher Thomas Ptacek published "How to Write with an LLM" on September 17, 2026, arguing that LLMs ruin your writing the moment you let them choose your words, but can meaningfully improve it as a strict, encouragement-free copyeditor. The essay hit 390 points on Hacker News, drew 270 comments, and — pointed out almost immediately — contains the word "load-bearing" in its own main text, an AI writing tell the essay itself warns against.

Sep 16

Sep 16

Sep 16

Jev is TypeSafe AI's first "System One Model": no text generation, just parallel, schema-guaranteed decisions with confidence scores, claimed to be 20-200x faster and 40-400x cheaper than LLMs for structured tasks. Here's what it actually does, what Hacker News pushed back on, and where it fits next to the LLM you're already using.

Sep 16

Sep 10

Sep 9

"I'll tip you $200," "act like the world's best engineer," "my job depends on this" — coaxing prompts are everywhere. explainx.ai checks the actual published research: what has real, measured effect, what's folk wisdom that doesn't replicate, and what to write instead for coding agents.

Sep 9

Separate from what a lab does to your account for being abusive, there's a narrower empirical question: does hostile tone change what a model actually outputs? Multiple studies disagree with each other — here's what they measured, why the results conflict, and what to do about it.

Sep 8

Elis "elvis" Fernandez surfaced a short prompt Anthropic shared days ago targeting "mannered prose" — the metaphor-heavy, flourish-first writing style AI models default to. He reports it improved writing on Fable 5.1 and, unexpectedly, GPT-5.6 Sol too. Full prompt text, why it works, and where to add it.

Aug 16

On August 15, 2026, Pliny the Liberator published the full 391,439-character system prompt, tool schema, and skill playbooks for Z.ai's ZCode coding agent — the harness built around GLM-5.3. The leak's most striking finding isn't the size; it's how closely ZCode's tool names and skill files mirror Claude Code's.

Aug 15

Doug Turnbull's "don't classify, hallucinate" post (216 points, 85 comments on Hacker News) flips structured-output classification on its head: instead of shipping a 500-category taxonomy to the LLM on every call, ask a cheap model to invent a plausible-sounding category, then embed that hallucination and nearest-neighbor it against real categories. It works because it's really HyDE (Hypothetical Document Embeddings) applied to classification instead of search.

Aug 4

A widely-discussed essay argues that the biggest multiplier on LLM output quality isn't clever prompting — it's how much domain expertise the user brings to the conversation. Terence Tao's math chat with ChatGPT is the proof, and the implications reach far beyond mathematics.

Aug 3

Every major AI lab recommends structured prompts with role, task, format, and context. explainx.ai names that checklist FROG in a Bowl so you can recall it under pressure — and stop shipping vague one-liners.

Jul 26

Prompts change instructions, RAG changes accessible knowledge, and fine-tuning changes learned behavior. Diagnose the failure before choosing the treatment.

Jul 7

On July 7, 2026, Ethan Mollick argued prompting tricks lost value before the agentic era — management beats magic words. explainx.ai maps his tweet to Wharton Generative AI Labs' Prompting Science Reports 1–4 on GPQA, MMLU-Pro, chain-of-thought, and expert personas.

Jul 7

The system_prompts_leaks repo archives extracted instructions for Claude Fable 5, GPT-5.5 Codex, Gemini 3.5 Flash, Cursor, Copilot, and dozens more. Here's how to use the corpus responsibly — and what it means for your product prompts.

Jun 29

JSON-in-prompt extraction fails on malformed source documents. tool_use with a JSON schema gives you schema-enforced output and a clean retry path when extraction fails. This is the structured output pattern the CCA exam tests.

Jun 27

"It works" is not a metric. Prompt engineering without evals is superstition. This guide shows you how to treat prompts like code — with test suites, A/B testing, regression guards, and metrics you can track over time.

Jun 27

ReAct is not a framework feature — it is a prompting pattern. Once you understand the Thought/Action/Observation loop you will see it everywhere: in LangChain agents, Claude Code, and every serious agentic system built in 2024 and beyond.

Jun 27

"Respond with JSON" breaks in production. This guide covers every approach to structured LLM output — from prompt hacks to native JSON mode to typed schemas — so you can pick the right one and validate it correctly.

Jun 22

Shortlist of 20 explainx.ai prompt generators for AI Agents, spanning audio, text modalities and 9 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Analytics, spanning audio, image, text modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for API Design, spanning audio, text, video modalities and 9 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Audio & Voice, spanning audio, image, text modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Software Development, spanning audio, text, video modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Content Strategy, spanning audio, image, text modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Customer Support, spanning audio, image, text modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Data Analysis, spanning audio, text modalities and 9 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Design, spanning audio, image, text, video modalities and 11 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for DevOps & Infra, spanning audio, image, text, video modalities and 11 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Technical Documentation, spanning audio, text, video modalities and 9 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Email & Newsletter, spanning audio, text modalities and 9 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Finance, spanning audio, image, text modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Frontend Development, spanning audio, text modalities and 9 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for HR & Recruiting, spanning audio, image, text modalities and 10 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Image Generation, spanning audio, image, text, video modalities and 12 high-level categories.

Jun 22

Shortlist of 20 explainx.ai prompt generators for Marketing, spanning audio, image, text, video modalities and 12 high-level categories.

Jun 22

Jun 22

Jun 22

Jun 22

Jun 22

Jun 22

Jun 22

Jun 22

Jun 22

Jun 16

Jun 16

Jun 16