Tag feed

#prompting

83 posts3 followers

Explore Hashnode

Alternatives

Trending tags this week

AGAlan Gornickblog.ag3-design.comMay 31 · 11 min read

Free Your LLM to Pursue Goals, Not Follow Rules

This guide and its prompt tools are updated as the method evolves. Schema-shots emerged from a practical problem: rules were brittle, detailed examples (shots) were powerful, but bulky. I needed a com

3

LA

AGAlan Gornickblog.ag3-design.comMay 25 · 17 min read

Show, Don't Tell: Shot-Focused and Schema-Shot Prompting

Testing my prompt library on small local models was humbling. Prompts that ran beautifully on frontier models dropped rules, stumbled, and broke. Experimentation taught me that the amount of text in a

1

V

QLQuokka Labsquokkalabs.hashnode.devMay 4 · 3 min read

Why Prompt Injection Is ALSO a Data Security Problem

Prompt injection is often framed as an AI issue. It is described to manipulate model behavior, override instructions, or bypass guardrails. While that is true, it misses the bigger picture. Prompt inj

0

ATAditya Trivediadityatrivedi.hashnode.devMay 1 · 10 min read

Advanced Prompt Engineering Guide: Fundamentals to Multimodal

What is a Prompt ? A prompt is an input to a Generative AI model, that is used to guide its output. It may consist of text, image, sound, or other media. The ability to prompt models, especially with

0

COChidiadi Oscarai-generalist.hashnode.devApr 30 · 3 min read

The Real Reason Your AI Outputs Feel Inconsistent

If you have ever felt that AI tools are inconsistent, you are not alone. The common reaction is to assume the model is unreliable but in most cases, the inconsistency does not come from the system, it

0

AAAbstract Algorithmsabstractalgorithms.devApr 17 · 20 min read

LLM Software Development Pitfalls: What to Avoid and When to Simplify

TLDR: Most bad LLM products do not fail because the model is weak. They fail because teams wrap a maybe-useful model in too much architecture: prompt spaghetti, no eval harness, weak tool schemas, hug

0

VDVíctor Dalhambraaxiom-mcp.hashnode.devApr 17 · 3 min read

The Prompt Compiler — a meta-prompt that generates prompts for you

I just published something I've been using daily: a meta-prompt that generates optimized prompts for me. The problem Most people write prompts the same way: dump everything into a chat, hope the model figures it out, iterate 4 times. Then the 4th ver...

0

RSRahul Sehrawatai-zero-to-hero.hashnode.devApr 12 · 11 min read

Finetune vs Prompt vs Retrieve — When to Use What

Here is the single most common mistake I see teams make when they start building with LLMs. Someone says "the model doesn't know about our stuff." A smart-sounding engineer nods and says "we should fine-tune it on our data." A project gets scoped. A ...

0

RSRahul Sehrawatai-zero-to-hero.hashnode.devApr 12 · 11 min read

Prompting As a Skill, Not a Trick

At some point in 2023, "prompt engineering" briefly became a job title you'd see on LinkedIn with a six-figure salary attached. There were viral tweets claiming secret incantations that would unlock hidden capabilities in ChatGPT. There were courses....

0

NRNick Robbofficial-intelligence.hashnode.devMar 6 · 5 min read

Stop Trying to Learn AI. Just Start Talking.

Everyone keeps saying you need to "learn AI." Take a course. Watch tutorials. Study prompt engineering. Here's the thing: you already know how to use AI. You've been doing it your whole life. It's called talking. The Myth That's Holding You Back I he...

0

#prompting

Search Hashnode

#prompting

Explore Hashnode

Trending tags this week

Free Your LLM to Pursue Goals, Not Follow Rules

Show, Don't Tell: Shot-Focused and Schema-Shot Prompting

Why Prompt Injection Is ALSO a Data Security Problem

Advanced Prompt Engineering Guide: Fundamentals to Multimodal

The Real Reason Your AI Outputs Feel Inconsistent

LLM Software Development Pitfalls: What to Avoid and When to Simplify

The Prompt Compiler — a meta-prompt that generates prompts for you

Finetune vs Prompt vs Retrieve — When to Use What

Prompting As a Skill, Not a Trick

Stop Trying to Learn AI. Just Start Talking.