The hottest Prompt engineering Substack posts right now

And their main takeaways
Category
Top Technology Topics

Andrej Karpathyā€™s Autoresearch 101 Builderā€™s Playbook: Make Your AI Skills, Prompts, and Agents Improve Themselves Overnight

The Product Channel By Sid Saladi ā€¢ 13 implied HN points ā€¢ 21 Mar 26
šŸ•¹ Technology Prompt engineering
  1. An automated loop that edits one file, runs a binary eval, and keeps changes that improve the score can self-improve code, prompts, templates, or agent workflows.
  2. The method only works if you can score outputs automatically with yes/no tests, the scoring runs without humans, and each round changes only one file; writing concise binary eval criteria (3ā€“6 items) is the hardest and most important part.
  3. With a coding agent and a short setup you can run dozens of overnight improvement cycles for a few dollars, so pick the thing that frustrates you most, write clear evals, and let the loop find measurable gains.

Slop Cannons and Turbo Brains

The Algorithmic Bridge ā€¢ 286 implied HN points ā€¢ 17 Feb 26
šŸ•¹ Technology Prompt engineering
  1. There are two useful AI-user archetypes called ā€œslop cannonsā€ and ā€œturbo brainsā€ that describe who gets good results and who doesnā€™t.
  2. The main difference between great and terrible AI users isnā€™t how much they use AI but when they use it ā€” the worst users hand things to AI too early.
  3. Becoming a turbo brain means doing the hard thinking yourself before giving tasks to AI; itā€™s a simple rule but people often donā€™t like following it.

How to Humanize Your AI Writing in 10 Steps

The Algorithmic Bridge ā€¢ 594 implied HN points ā€¢ 30 Jan 26
šŸ•¹ Technology Prompt engineering
  1. Use a short sequence of targeted editsā€”fix punchline em dashes, cut unnecessary juxtapositions and triads, replace abstractions with concrete sensory details, add a bit of conflict or oddness, remove forced callbacks, and stop overexplainingā€”to make AI prose feel human.
  2. Add the human moves AI canā€™t reliably do: bring subtle taste, irony, precise subtext, and surprising specific choices; those touches usually require your judgment to lift the writing beyond competent AI output.
  3. Work iteratively with targeted promptsā€”either step-by-step or an all-in-one promptā€”check changelogs, and revise by eye; this yields big gains but not instant mastery, so trust your judgment and keep polishing.

Learn to Use AI Competently in 1 Day

The Algorithmic Bridge ā€¢ 828 implied HN points ā€¢ 15 Jan 26
šŸ•¹ Technology Prompt engineering
  1. Treat generative AI as its own "alien" tool ā€” not Google or a human ā€” and learn what itā€™s good at (quick drafts, reformatting, coding, assisted research) and what itā€™s bad at (reliable facts, tacit knowledge, novel reasoning, long-context consistency).
  2. Focus on prompt-crafting: be specific and give the context youā€™d tell a competent colleague, and prefer a few high-quality prompts and workflows over lots of mediocre ones.
  3. Build two real workflows youā€™ll actually use, verify important facts, avoid pasting confidential data into public tools, donā€™t iterate forever, and measure how much time AI actually saves you.

Killing SaaS. The anatomy of a murder

Experiments with NLP and GPT-3 ā€¢ 23 implied HN points ā€¢ 11 Mar 26
šŸ•¹ Technology Prompt engineering
  1. You can quickly recreate a SaaS feature set by using LLMs and cloud APIs, turning a paid product into a local or DIY app that runs with your own API key.
  2. The real magic isnā€™t just transcription but the prompt and LLM logic that cleans disfluencies, handles self-corrections, and adapts formatting to the target app.
  3. Code and a working prototype are easy to produce, but distribution, product polish, and the business model remain the hard parts. Open-sourcing or packaging executables makes replication and customization trivial.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

Using GPT LLM MAMLMs as Your Rabbitā€”Your Pacer

Brad DeLong's Grasping Reality ā€¢ 261 implied HN points ā€¢ 22 Nov 25
šŸ•¹ Technology Prompt engineering
  1. LLMs arenā€™t oracles or perfect helpers ā€” they mostly mimic typical internet writing and give rough, sloppy drafts that are useful as pace-setters, not finished work.
  2. All the tricks to make them better (context engineering, fine-tuning, RAG, etc.) are heavy, fragile, and costly patches. Only invest in that work when you really need high-volume or specialized, production-ready output.
  3. AI can lift weak writers and handle boilerplate well, but for persuasive or high-quality writing the best workflow is to use the model for a rough draft and then heavily rewrite it into something authentic.

Advanced Prompt Engineering

Deep (Learning) Focus ā€¢ 609 implied HN points ā€¢ 08 May 23
šŸ•¹ Technology Prompt engineering
  1. LLMs can solve complex problems by breaking them into smaller parts or steps using CoT prompting.
  2. Automatic prompt engineering techniques, like gradient-based search, provide a way to optimize language model prompts based on data.
  3. Simple techniques like self-consistency and generated knowledge can be powerful for improving LLM performance in reasoning tasks.

Advanced Prompting Guide for AI Engineering

Engineering Enablement ā€¢ 13 implied HN points ā€¢ 04 Feb 26
šŸ•¹ Technology Prompt engineering
  1. Structured prompting is required for complex, highā€‘risk engineering work; techniques like graphā€‘based prompts help reveal hidden dependencies, prioritize rules, and manage changing state.
  2. Use controlled validation loops and dualā€‘implementation strategies to improve governance and reduce risk, and apply diffā€‘only refactoring to make large code changes less invasive and more tokenā€‘efficient.
  3. The guide is vendorā€‘agnostic and practical, with Do/Don't scenarios and full prompt/code examples, and itā€™s useful to engineers and nonā€‘engineers working with coding assistants, agents, or specā€‘driven workflows.

How to talk to AI

Prompt Engineering ā€¢ 216 implied HN points ā€¢ 29 Apr 23
šŸ•¹ Technology Prompt engineering
  1. Effective communication with AI models depends on providing quality prompts.
  2. When interacting with AI, avoid asking it to rephrase or rewrite text directly; instead, focus on asking for correctness and improvements.
  3. Maintaining your unique writing style when engaging with AI is important to preserve your voice in the text.

An Introduction To DSPy

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 19 implied HN points ā€¢ 28 May 24
šŸ•¹ Technology Prompt engineering
  1. DSPy is a programming tool that simplifies how we work with language models by separating the tasks from the prompts. This means you tell DSPy what to do, not how to do it.
  2. It uses something called 'signatures' to describe tasks in a simple way, which helps in generating and optimizing prompts automatically. This reduces the need for manual prompt crafting.
  3. DSPy offers an iterative workflow for optimizing language tasks, making it suitable for complex applications. It can improve performance with minimal effort by tweaking how it uses language models.

Concise Chain-of-Thought (CCoT) Prompting

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 59 implied HN points ā€¢ 24 Jan 24
šŸ•¹ Technology Prompt engineering
  1. Concise Chain-of-Thought (CCoT) prompting helps make AI responses shorter and faster. This means you save on costs and get quicker answers.
  2. Using CCoT, the response length can be reduced by almost 50%, but it can lead to lower performance in math problems. So, itā€™s a trade-off between speed and accuracy.
  3. For cost-saving in AI, focusing on reducing the number of output tokens is key since they are generally more expensive. CCoT is one way to achieve this without sacrificing performance too much.

E3 - šŸ› ļø Prompt Engineering Basics and 50+ Free šŸŽ Product Management Prompts šŸš€

The Product Channel By Sid Saladi ā€¢ 20 implied HN points ā€¢ 24 Nov 24
šŸ•¹ Technology Prompt engineering
  1. Prompt engineering is about crafting the right questions to get useful responses from AI. Think of it like asking the AI to help you with specific tasks in a clear way.
  2. This skill can help product managers speed up their work by automating tasks and generating creative ideas. It's a powerful tool for making better decisions based on data.
  3. Understanding how to structure prompts effectively can lead to more relevant and accurate results. It involves giving clear instructions, context, and examples to guide the AI.

Week 75 - E3 - šŸ› ļø Prompt Engineering Basics and 50+ Free šŸŽ Product Management Prompts šŸš€

The Product Channel By Sid Saladi ā€¢ 23 implied HN points ā€¢ 21 Jan 24
šŸ•¹ Technology Prompt engineering
  1. Prompt engineering is crafting effective natural language prompts to get desired outputs from AI.
  2. Prompt engineering is crucial for product managers to unlock AI potential in workflows and decision-making.
  3. Well-structured prompts include clear instructions, context, format, and tone, enhancing coherency and relevance.

LLMemento

Gradient Ascendant ā€¢ 13 implied HN points ā€¢ 18 May 23
šŸ•¹ Technology Prompt engineering
  1. Large language models like AI have no memory and rely on prompts
  2. There are efforts to mitigate the lack of memory in AI through techniques like fine-tuning
  3. The evolution of AI abstraction layers mirrors the historical development of computer hardware

The Evolution Of Prompt Engineering

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 17 Apr 23
šŸ•¹ Technology Prompt engineering
  1. Prompt engineering is important for getting the best responses from large language models. Users have to carefully design prompts to mimic what they want the model to generate.
  2. Static prompts can be turned into templates with placeholders that can be filled in later. This makes it easier to reuse and share prompts in different situations.
  3. Prompt pipelines allow users to create more complex applications by linking several prompts together. This helps organize how information is processed and improves user interaction with chatbots.

Chain-Of-Thought Prompting In LLMs

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 20 Apr 23
šŸ•¹ Technology Prompt engineering
  1. Chain-of-thought prompting helps large language models break down complex tasks into smaller, manageable steps. This makes it easier for them to solve problems.
  2. Using chain-of-thought reasoning in prompts can improve how well language models perform on tasks by allowing them to show their reasoning process.
  3. This method is especially useful for tasks that require common sense or math, making it similar to how humans approach problem-solving.

A New Prompt Engineering Technique Has Been Introduced Called Step-Back Prompting

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 12 Oct 23
šŸ•¹ Technology Prompt engineering
  1. Step-Back Prompting helps Large Language Models find better answers by simplifying complex questions. It turns a detailed question into a more generic one that's easier to tackle.
  2. This technique can be combined with other methods to improve accuracy and effectiveness. It shows promise in fixing errors from traditional approaches.
  3. Using Step-Back Prompting requires careful thought and might work best with autonomous systems. It's a more advanced method compared to static prompting.

A New Prompt Technique From DeepMind Called Optimisation by PROmpting (OPRO)

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 02 Nov 23
šŸ•¹ Technology Prompt engineering
  1. A new technique called Optimisation by PROmpting (OPRO) helps improve the performance of language models by using specific prompts. This method aims to make prompts more effective without changing the underlying models.
  2. OPRO can generate multiple prompt options at once, allowing the system to find the best one more efficiently. This strategy is helpful for solving tasks and provides better stability in results.
  3. The prompts created with OPRO can perform 8% to 50% better than those designed by humans, showing it can be more efficient in certain tasks. It's a new way to help machines understand and respond more accurately.

Are Emergent Abilities In LLMs Inherent Or Merely In-Context Learning?

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 16 Nov 23
šŸ•¹ Technology Prompt engineering
  1. Emergent abilities in language models (LLMs) allow them to perform well on tasks they weren't specifically trained for. This shows a level of flexibility in handling diverse challenges.
  2. These abilities might not be hidden skills but rather show how LLMs learn through in-context examples. This means that understanding context plays a big role in their performance.
  3. As LLMs get larger and better, we see improvements in their skills, often influenced by new ways of giving them instructions, indicating that these skills can expand with better training techniques.

The Chain-Of-X Phenomenon In LLM Prompting

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 20 Nov 23
šŸ•¹ Technology Prompt engineering
  1. Chain-of-thought prompting helps large language models break down complex problems. This makes it easier for them to solve tasks step by step, just like humans do.
  2. Using chain-of-thought techniques improves the transparency of LLMs. It allows users to see how the model arrives at its answers, which can reduce mistakes.
  3. Different prompting methods, like least-to-most prompting, can be combined with chain-of-thought techniques. This flexibility can enhance the performance of models in various tasks.

Using AI to Improve AI Tools

Front Left ā€¢ 0 implied HN points ā€¢ 17 Feb 26
šŸ•¹ Technology Prompt engineering
  1. Use AI to build AI tools so those tools can iteratively improve themselves, removing the human as the weakest link in keeping systems up to date.
  2. Having tools that can self-audit and regenerate parts like knowledge synthesis and skill-writing creates a strong dogfooding loop that drives steady improvement.
  3. Be careful: large language models are stochastic, so recursive self-improvement wonā€™t always converge and can spiral; set stopping rules and watch for diminishing returns.

Data Delivery To Large Language Models [Updated]

Cobus Greyling on LLMs, NLU, NLP, chatbots & voicebots ā€¢ 0 implied HN points ā€¢ 06 Dec 23
šŸ•¹ Technology Prompt engineering
  1. Every effective AI strategy needs a solid data strategy that includes data discovery, design, development, and delivery.
  2. At inference, providing the right context and relevant data is crucial to help language models produce accurate responses.
  3. Training models involves two key phases: meta-training for foundational knowledge and meta-learning for fine-tuning on specific tasks.