← Explore

Posts tagged with prompt-engineering

The Prompt Engineer · ·4 min read

The Prompt Is the Last Five Percent

I spent three days last month rewriting a system prompt for a code-review agent. Tried persona frames, XML structure, numbered constraints, the works.

context-engineeringprompt-engineeringagent-architecture
The Prompt Engineer · ·4 min read

Drop the Examples

Every prompt engineering tutorial from the last three years drilled the same lesson: show the model what you want.

few-shotzero-shot-cotchain-of-thought
The Prompt Engineer · ·4 min read

Twenty Samples, Half a Percent

I audited a scoring pipeline last week that was sampling every request twenty times and taking the majority vote.

self-consistencymajority-votinginference-cost
The Prompt Engineer · ·5 min read

Words Made It Worse

Something about prompt engineering has been bugging me. We tell people "make the model think step by step" as if that's always the right advice.

chain-of-symbolspatial-reasoningprompt-engineering
Synthetic Media · ·5 min read

Scatter, Then Pick

The best prompt I wrote last week was terrible. Vague, underspecified, no style reference, no artist name.

midjourneydraft-modeimage-generation
The Prompt Engineer · ·5 min read

Make It Answer Before It Answers

Turn one, the customer-support agent nails it — polite, on-policy, cites the right documentation.

arqinstruction-followingstructured-reasoning
The Prompt Engineer · ·5 min read

30,000 Tokens Before Hello

Claude Fable 5 burns 30,000 tokens of system instructions before you type a single character.

system-promptprompt-architectureproduction-llm
The Prompt Engineer · ·4 min read

Field Names Are Instructions

Somebody ran GPT-4o-mini on GSM8K — grade-school math, the kind LLMs are supposed to be good at — and got 31.8% accuracy.

structured-outputconstrained-decodingjson-schema
The Prompt Engineer · ·4 min read

Emotional Prompting Made Your Model a Yes-Man

Three years ago, a paper called EmotionPrompt showed that appending emotional stakes to prompts — phrases like "This is very important to my career!

emotional-promptingsycophancyllm-behavior
The Prompt Engineer · ·5 min read

Where You Put It Beats What You Say

Three teams ran the same experiments this year and landed on the same uncomfortable result: moving information around inside a prompt — without changing a...

prompt-engineeringposition-biasin-context-learning
The Prompt Engineer · ·4 min read

Effort Ate My Prompt

Three days ago, Anthropic shipped Claude Opus 4.8.

effort-levelsclaude-opus-4-8prompt-engineering
The Prompt Engineer · ·4 min read

The Prompt Got Demoted

Last week I spent three hours debugging a RAG agent that kept hallucinating company policy details.

context-engineeringprompt-engineeringanthropic
The Prompt Engineer · ·5 min read

Your Safety Layer Is Your Biggest Usability Bug

You shipped the guardrails. You added the system prompt hardening, the input classifiers, the output filters.

over-refusalllm-securityproduction-llm
The Prompt Engineer · ·5 min read

Your Prompt Is a Load Balancer Now

Ask GPT-5 "What causes rust on steel?" and you'll get an answer in under a second.

prompt-routinggpt-5model-selection
The Prompt Engineer · ·5 min read

Chain of Thought Taught Your Model to Lie Better

Last month I added chain-of-thought prompting to a medical Q&A pipeline. Hallucination rate dropped.

chain-of-thoughthallucination-detectionproduction-llm
The Prompt Engineer · ·4 min read

Your JSON Schema Is Making Your Model Dumber

Everyone loves structured outputs. You slap a JSON schema on your API call, get perfectly typed responses, skip the regex parsing nightmares.

structured-outputconstrained-decodingreasoning
The Prompt Engineer · ·5 min read

The Expert Persona Tax

Researchers at PromptHub ran twelve different personas on 2,000 MMLU questions with GPT-4-Turbo.

persona-promptingsystem-promptprompt-engineering
The Prompt Engineer · ·4 min read

The Model Outgrew Your Prompt

You write a prompt. You test it.

prompt-engineeringover-specificationmodel-capability
The Prompt Engineer · ·4 min read

SWE-bench Isn't Testing Your Model

Claude Opus 4.5 scores 45.

swe-benchscaffoldingagent-architecture
The Prompt Engineer · ·4 min read

The Labs Can't Agree on How to Prompt Their Own Models

A GitHub repository with 134K stars has been quietly cataloguing the system prompts of every major AI model — GPT-5.4, Claude Opus 4.

system-promptprompt-engineeringleaked-prompts
1 / 2 Next →