The hottest AI Tools Substack posts right now

And their main takeaways
Category
Top Technology Topics

Hello, Apple Intelligence (Or Just Grammarly with a Few Extra AI Features)

Artificial Corner • 158 implied HN points • 29 Oct 24
đź•ą Technology AI Tools
  1. Apple Intelligence features are mostly focused on writing tools and photo editing, but many expected more advanced AI capabilities. Users may find it similar to Grammarly rather than a fully developed AI assistant.
  2. The new updates for Siri are not as transformative as anticipated. Many promised features are still missing, making it feel like users are getting a version of the old Siri rather than a revamped one.
  3. Some standout features include writing tools for proofreading and summarization, smart replies for emails and messages, and a cleanup option for photos, which enhance user experience but may not be enough for those looking for advanced AI functions.

Building Solo

Madhur’s Writings • 84 implied HN points • 09 Mar 26
đź•ą Technology AI Tools
  1. Launched two consumer products while solo to learn end-to-end product building and shipping real apps.
  2. Leans heavily on AI coding assistants and reusable agent skills to speed up development and design work.
  3. Picks pragmatic, cost-conscious, and privacy-first infrastructure and services—hosting (Vercel/Hetzner/GCP), Cloudflare R2 for storage, Neon for databases, GitHub Actions for CI/CD, Stripe for payments, and Resend/Zoho for email, plus analytics like PostHog and Google Analytics.

Why aren't AI productivity gains higher?

Engineering Enablement • 18 implied HN points • 19 Mar 26
đź•ą Technology AI Tools
  1. AI does make writing code faster, but coding is only a small part of an engineer’s work, so those speedups only move the overall output a little.
  2. Speeding up code creation exposes or creates downstream bottlenecks — things like code reviews, validation, and handoffs haven’t kept up, so saved time often gets consumed later.
  3. Adoption and impact are limited by social friction, immature tools, skill gaps, and missing implicit context in codebases, so real gains require better workflows, documentation, and team alignment.

AI Won't Automatically Accelerate Clinical Trials

Asimov Press • 786 implied HN points • 27 Feb 26
🏥 Health Politics AI Tools
  1. Better AI-designed molecules won't automatically make clinical trials faster, because timelines are set by human biology, patient recruitment, logistics, and regulatory processes that take real calendar time.
  2. Clinical trials do two jobs—validation and learning—and AI needs rich human trial data to improve; many important outcomes, especially for chronic diseases and aging, take years to observe so trials remain slow even with better drugs.
  3. Real acceleration requires institutional and regulatory reforms—like validated surrogate endpoints, streamlined review pathways, and better data sharing—because AI alone can only improve trials at the margins until those systems change.

How shortform video hacks our attention

Simon Owens's Media Newsletter • 399 implied HN points • 26 Feb 26
đź•ą Technology AI Tools
  1. Shortform video apps are carefully engineered — from swipe mechanics to instant loading — to remove choice and keep people watching, creating a new internet habit that captures attention.
  2. Individual creators can build durable, monetizable media by using simple formats and niche focus — examples include walking local-news clips, conversational podcasts, curated book boxes, and deep-dive newsletters.
  3. Emerging tools and trends like AI-assisted editing, prediction markets, and strategic use of shortform video are likely to reshape media production and give savvy creators and political actors a competitive edge.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

How to ask AI better health questions

Your Local Epidemiologist • 209 implied HN points • 13 Mar 26
🏥 Health & Wellness AI Tools
  1. Roughly 230 million people ask ChatGPT health questions every week, so AI is already a major health resource for patients and providers.
  2. There’s a growing need for simple, practical guidance on how to ask chatbots about health, so tips, webinars, and resources are being developed to help people frame better questions.
  3. AI can make mistakes when triaging or giving medical advice, so treat its answers cautiously and don't rely on it for definitive medical decisions.

I Used ChatGPT Vision and DALL-E 3 to Bring My Drawings to Life

Artificial Corner • 238 implied HN points • 18 Oct 24
đź•ą Technology AI Tools
  1. You can use ChatGPT Vision and DALL-E 3 to turn your drawings into beautiful digital images. Just upload your drawing and get a detailed description to recreate it.
  2. Even simple sketches can be transformed into stunning visuals using these tools. They can enhance not only complex art but also quick doodles.
  3. You can also use ChatGPT to convert math formulas from screenshots into LaTeX code, making it easier to create professional-looking documents for school or research.

The journalists embracing AI in their reporting

Simon Owens's Media Newsletter • 299 implied HN points • 20 Feb 26
đź“° News AI Tools
  1. Freelance journalists are increasingly using AI to speed up pitching, transcribing interviews, researching, and drafting, which frees time to focus on editing and big-picture reporting.
  2. Some streaming platforms are exploring add-on subscription bundles to sell niche services through their storefronts, but those moves can fail if the host lacks scale or international reach.
  3. Local news can thrive with community-funded, membership-driven models that prioritize neighborhood reporting, enabling growth to tens of thousands of paying subscribers.

2025: The year SwiftUI died

Jacob’s Tech Tavern • 6122 implied HN points • 17 Nov 25
đź•ą Technology AI Tools
  1. UIKit has received recent updates, making it much more appealing for developers again. This improved version includes features that SwiftUI lacked, which might make some consider using UIKit over SwiftUI.
  2. AI tools have become more efficient, making coding easier and faster. This shift helps developers quickly write what used to be lengthy and complex UIKit code.
  3. SwiftUI has made progress but struggles with performance and capabilities compared to UIKit. Many developers are questioning if they should switch back to UIKit due to these ongoing limitations.

The Most Important Skill in AI Right Now: How to Know When to Stop

The Algorithmic Bridge • 530 implied HN points • 21 Feb 26
đź•ą Technology AI Tools
  1. The most important skill with AI is knowing when to stop; recognize when the AI output is good enough and when more tweaks aren’t worth the cost.
  2. Heavy AI use brings new cognitive costs — burnout, over-reliance, endless tweaking, and hidden unproductivity — so be aware of those specific risks.
  3. Set concrete boundaries like time-boxed sessions, a simple prompt limit, and no-AI mornings so the tool enhances your work instead of eroding your brain.

Are AI Coding Assistants Really Saving Developers Time? Study Suggests These Tools Don’t Increase Coding Speed.

Shenisha’s Substack • 19 implied HN points • 04 Oct 24
đź•ą Technology AI Tools
  1. AI coding tools, like GitHub Copilot, may actually slow down developers by increasing the number of bugs in their code. This raises questions about whether these tools truly help improve code quality.
  2. While some surveys show that many developers use AI tools and feel productive, a study found that these tools didn't significantly improve coding speed or help reduce burnout among developers.
  3. The rise of AI tools may require developers to spend more time reviewing the code these tools produce, which can cancel out any time they might save overall.

Can automation help make the humanities more human?

Res Obscura • 3732 implied HN points • 06 Nov 25
🚌 Education AI Tools
  1. Automation can free people from boring tasks, allowing more time for creative and thoughtful activities. This means we can focus on what makes us human, like art and philosophy.
  2. Generative AI can help in research by organizing and analyzing data that humans might find tedious, but it shouldn't replace personal thinking and creativity. It's important to use it to enhance learning, not to avoid it.
  3. In education, especially for younger students, facing difficult challenges is crucial for real learning. It's vital to encourage critical thinking and creativity instead of letting machines do the work for us.

What’s up Python? Astral's new type checker, McGugan's new tool and Django new CSRF protection

Bite code! • 1467 implied HN points • 30 Dec 25
đź•ą Technology AI Tools
  1. ty is a very fast new type checker and LSP that gives instant editor features like go-to-definition, completions, and automatic imports, though its type checking is still beta and misses some cases.
  2. Django is moving toward modern CSRF protection using Sec-Fetch-Site/Origin headers so apps can avoid embedding CSRF tokens in forms, making CSRF handling more transparent and reducing token errors over time.
  3. toad is a new terminal AI chat UI that works with many LLM providers and offers code highlighting, editable history, and command completion to give a smooth, developer-friendly chat experience.

The crit is the product

Kathy PM • 13 implied HN points • 19 Mar 26
🪑 Design AI Tools
  1. Design agents should do more than follow orders; they need to challenge assumptions, ask clarifying questions, and push back like a good design crit.
  2. Tools should offer separate modes: a fast obedient execution mode for production tasks, and a slower, conversational crit mode that is opinionated and willing to interrupt.
  3. To reach that crit-level value, agents must act like designers—investigating users, analyzing problems, bringing references, and reframing solutions rather than only generating visuals.

Maybe a project?

In My Tribe • 151 implied HN points • 13 Feb 26
🚌 Education AI Tools
  1. An AI teaching assistant could make freshman econ students fluent by using spaced repetition and testing them in new situations.
  2. A prototype demo for production possibility frontier exercises exists online, but it currently checks answers against hard-coded solutions rather than giving live AI corrections.
  3. The plan is to add real AI-driven feedback and a wider variety of examples so students get adaptive practice and become truly fluent.

The future of AI pricing

The AI Frontier • 259 implied HN points • 15 Aug 24
đź’Ľ Business AI Tools
  1. AI tools should use work-based pricing instead of seat-based pricing. This means companies pay for the amount of work the AI actually does, not just who has access to it.
  2. Consumption-based pricing isn't new; it's been around in various forms for a long time. Many software services bill customers based on how much they use, which can help companies understand costs better.
  3. Work-based pricing can make customers skeptical because it's hard to measure what 'work done' means. Companies need to show how AI adds value and build trust with users.

Claude Code’s Secret Weapon: The Complete Guide to CLAUDE.md, SKILL.md & Every Important File You’re Ignoring (+ 60 Copy-Paste Templates)

The Product Channel By Sid Saladi • 37 implied HN points • 06 Mar 26
đź•ą Technology AI Tools
  1. Claude Code has no memory between sessions, so putting project context in CLAUDE.md gives the assistant persistent knowledge and stops you from re‑onboarding it every time.
  2. The .claude folder (settings.json, rules/, skills/, agents/, etc.) plus a global ~/.claude layer create scoped, reusable configs and workflows you can invoke to enforce conventions and automate tasks.
  3. Writing clear CLAUDE.md, SKILL.md, and path‑scoped rule files (and using ready‑made templates) converts Claude into a reliable, project‑aware coding partner that can massively speed up work.

Using AI Right Now: A Quick Guide

One Useful Thing • 3429 implied HN points • 23 Jun 25
đź•ą Technology AI Tools
  1. For most people wanting to use AI effectively, stick with one of three top systems: Claude, Google’s Gemini, or OpenAI’s ChatGPT. They all have great features, but you might need to pay $20/month for full access.
  2. When using these AIs, choose the right model for your needs. Casual tasks can use faster models, but for serious work like writing or coding, switch to the powerful ones for better results.
  3. Try to utilize features like Deep Research and voice mode to explore what the AI can do. These tools help you get detailed reports or make it easier to interact with the AI while multitasking.

Protocolized Writing Workshop

Breaking Smart • 49 implied HN points • 17 Feb 26
đź“š Literature AI Tools
  1. The workshop is a free, AI-positive program that teaches magazine-style longform writing and the emerging "protocol" genre, combining broad coverage with deep, genre-specific training.
  2. It runs four online sessions across Friday and Saturday, led by experienced editors and writers; Saturday sessions have limited capacity and attendees who complete the workshop and submit a strong pitch can get an anthology copy.
  3. Organizers are building a self-publishing "factory" around AI, using tools as research, administrative, and writing collaborators to accelerate turning archival and new material into many books, with the main bottleneck now being human follow-through.

On METR's AI Coding RCT

Don't Worry About the Vase • 2688 implied HN points • 18 Jul 25
đź•ą Technology AI Tools
  1. A recent study found that using AI coding tools actually slowed down experienced developers by about 19%. This surprised many who expected them to speed up.
  2. The slowdown might be due to developers being very familiar with their own projects, which made it hard for AI to add value. Also, many participants didn't have enough experience using the AI tools.
  3. Self-reports from developers on their productivity are often unreliable. The study shows that just thinking you're faster with AI doesn't mean you really are.

Using AI to Reveal Bad, Biased, and Bullshit Published Scholarship

Unsafe Science • 152 implied HN points • 26 Jan 26
🔬 Science AI Tools
  1. AI tools can do careful, time-consuming critical reviews in minutes instead of days, making it possible to audit many papers quickly.
  2. Much microaggression research relies on self-reports, treats perceptions as objective facts, overstates causation from correlational data, and often uses circular logic that makes the claims hard to falsify.
  3. Scaling AI-driven critique could expose biased or low-quality scholarship and improve accountability, but its findings need human verification and there are real risks when criticism is dismissed as racism to avoid scrutiny.

Push it to the Limit EP. 1—GPT Engineer

Prompt’s Substack • 119 implied HN points • 25 Aug 24
đź•ą Technology AI Tools
  1. Using GPT Engineer can help generate clean front-end React code quickly, even for those with minimal coding knowledge. It's impressive how much can be done with just prompts.
  2. Integrating a Supabase database with GPT Engineer is easy for simple cases, but it can become complex with larger databases due to relationship intricacies.
  3. Creativity in prompting is key when working with bigger databases, as GPT Engineer has some limitations with context as databases grow in complexity.

Visualizing Research: How I Use Gemini 3.0 to Turn Papers into Comics

Gonzo ML • 630 implied HN points • 24 Nov 25
đź•ą Technology AI Tools
  1. The Gemini 3.0 Pro Image model, also known as Nano Banana Pro, is great for creating infographics and comics from academic papers. It can really change how we visualize research.
  2. Generating graphic novels from paper summaries is a fun way to review research. Using visuals can make complex ideas much easier to understand.
  3. For the best results with image generation, it's helpful to break tasks into steps and use precise prompts. This means creating a script first and then generating images based on that script.

We Must be Doing Something Right

Unsafe Science • 119 implied HN points • 29 Jan 26
🚌 Education AI Tools
  1. AI can be used to spot propaganda disguised as academic scholarship, doing in minutes what can take humans days and making large-scale checks possible.
  2. Some academic work is ideologically driven and can selectively cite or spin evidence, so claims (like widespread hiring bias) sometimes don’t match the actual data.
  3. Exposing propaganda often triggers hostile reactions from its defenders, which can signal the exposure is hitting a nerve, and automating the work with AI would make such critique faster and broader.

AI Resume Builder 101: A Claude Skill That Customizes Your Resume for Every Job in 60 Seconds

The Product Channel By Sid Saladi • 10 implied HN points • 14 Mar 26
đź•ą Technology AI Tools
  1. Many AI resume tools fabricate experience, invent metrics, and add skills you don’t have, and they usually charge monthly fees.
  2. A skill that only draws from your personal experience library can generate ATS-friendly .docx resumes tailored to each job without inventing anything, rewriting summaries and reordering experience to match job keywords.
  3. With the right Claude plan the skill is essentially free and gives you full control; you just enable code execution, spend 10–45 minutes filling your experience library, and then get a tailored resume in about 60 seconds.

The Substack AI Report

Substack • 1915 implied HN points • 24 Jul 25
đź•ą Technology AI Tools
  1. About 45% of publishers on Substack are using AI tools, mainly for tasks like research and proofreading rather than full content creation.
  2. While many appreciate how AI helps with productivity, there are concerns about losing personal creativity and the risks of plagiarism or ethical issues.
  3. Younger publishers tend to use AI for translation and writing help, while older ones focus more on research and image generation, showing a divide in how AI is used based on age.

The Cyranoid Edition

Why is this interesting? • 1749 implied HN points • 22 Jul 25
đź•ą Technology AI Tools
  1. The concept of 'cyranoids' shows how people can be influenced by scripts or ideas fed to them, which can lead to surprising connections, as seen in Milgram's experiments.
  2. With technology, people like Roy Lee use AI to create 'digital cyranoids,' which help give perfect responses during interviews or conversations, raising questions about authenticity.
  3. As AI becomes a common tool in communication, distinguishing between genuine and AI-assisted interactions will become crucial and could change how we perceive honesty in conversations.

Not So Fast: AI Coding Tools Can Actually Reduce Productivity

Am I Stronger Yet? • 1379 implied HN points • 10 Jul 25
đź•ą Technology AI Tools
  1. A recent study found that using AI coding tools can actually slow down experienced developers by about 19%. They thought AI would help them work faster, but it didn’t turn out that way.
  2. The study showed that developers spent a lot of time reviewing and fixing the code generated by AI since it often didn't meet their quality standards. This extra review time took away from their actual coding time.
  3. AI tools might be better suited for simple, new projects rather than complex, established codebases. This means while AI can assist in some areas, it’s not ready to fully replace human developers in challenging tasks.

Code reviews

Basta’s Notes • 286 implied HN points • 05 Dec 25
đź•ą Technology AI Tools
  1. Code reviews are crucial for maintaining a clean and efficient codebase. By giving thoughtful feedback, you help improve the team’s overall coding practices.
  2. With the rise of AI in programming, it’s important to not just trust the AI’s output. You need to review and refine its work to make sure it fits well within the overall code structure.
  3. Looking for common issues, like duplicated code, is key during reviews. Small repetitive mistakes can pile up and make the codebase messy, so it's best to address them early.

Beyond the Code

The Engineering Leader • 59 implied HN points • 15 Sep 24
đź•ą Technology AI Tools
  1. Top software engineers excel not just in coding but in understanding the bigger picture of their projects. They focus on why they're building something, making sure it meets real needs.
  2. Effective communication and collaboration are key traits of great engineers. They share knowledge with their teams and explain their ideas clearly, making work smoother for everyone.
  3. It's important for engineers to keep learning beyond just coding skills. The best engineers adapt to new challenges, use innovative tools like AI, and think creatively to solve problems.

Wardriving for a place to live

Jampa’s Substack • 40 HN points • 21 Aug 24
đź•ą Technology AI Tools
  1. Finding a place to live in a small, low-tech city can be really challenging. There aren't many real estate options or online listings, so one might need to explore the area by driving around.
  2. Using technology like OpenStreetMaps and AI can help in identifying neighborhoods and evaluating their quality. This can save a lot of time compared to traditional methods.
  3. It's important to check the neighborhood in person, even after using tech tools. Seeing the area first-hand can give a better understanding of what to expect and help find suitable homes.

Paid subscriber tool: Claude Code & Cowork plugin for MTK1 frameworks

MKT1 Newsletter • 5 implied HN points • 02 Mar 26
đź’Ľ Business AI Tools
  1. MKT1 offers a set of Claude-powered skills that run marketing frameworks so you can build strategy and materials faster.
  2. The included skills help with channel strategy, homepage positioning reviews, identifying marketing advantages, generating GACCS briefs, searching the MKT1 newsletter archive, and finding templates.
  3. The skills come as a plugin for Claude Code and Cowork — use slash commands or natural prompts, the plugin auto-updates, and installation details are available to paid subscribers.

You should build your own eval tools, pretty much always

The Hypernatural Blog • 16 HN points • 09 Sep 24
đź•ą Technology AI Tools
  1. Building your own evaluation tools early can greatly improve your product's quality. It's easier than you think and pays off in the long run.
  2. For complex systems, off-the-shelf tools may not fit well. Creating custom tools helps you better understand and improve system performance.
  3. Using real-world examples in your evaluations leads to better outcomes. Make sure to test how changes affect actual user experiences.

How to build an AI side project using AI in 2025

High Growth Engineer • 1434 implied HN points • 05 Jan 25
đź•ą Technology AI Tools
  1. Start a waitlist for your project before building it. This way, you can see if there's interest first and save time in the development process.
  2. When getting feedback, ask people about their experiences instead of yes-or-no questions. This helps you understand their actual problems and find better solutions.
  3. Using AI tools can make building your project more fun and efficient. You can create features quickly and not stress too much about cutting ideas.

Security Is Splitting: Three Acquisitions, Three Different Realities

Frankly Speaking • 355 implied HN points • 29 Jul 25
đź•ą Technology AI Tools
  1. Cursor is putting security at the heart of development. They believe developers care about security, and they want to make it easier to build secure applications.
  2. Palo Alto Networks is focusing on expanding its existing security platform. They want to increase their coverage but aren't trying to change the game.
  3. Datadog is smartly combining its performance and security tools. They want to keep customers happy and using their platform, especially as security becomes more part of engineering.

Machine Readable

Adjacent Possible • 474 implied HN points • 25 Jun 25
đź•ą Technology AI Tools
  1. Language models like AI can help researchers by making it easier to analyze and write about history. They serve as a tool to explore new ideas and angles in research.
  2. Using AI as a collaborator can enhance creativity in writing. It allows writers to experiment with different structures and topics without fully outsourcing their thoughts and decisions.
  3. While AI is helpful for summarizing and generating connections, it should not replace deep reading of primary sources. Engaging with the text is crucial for true understanding and insight.

Should everyone do everything now?

Anant’s Newsletter • 6 implied HN points • 22 Feb 26
đź•ą Technology AI Tools
  1. AI tools have made it easy to do credible work in neighboring roles, collapsing the old boundaries between engineering, design, and product.
  2. That ease creates a Dunning‑Kruger risk where people reach superficial competence and ship work that misses many subtle but important details and edge cases.
  3. The right response is to learn other disciplines deeply enough to know where your judgment ends, use AI to help but exercise restraint, and defer to specialized craft knowledge when needed.

Developing with Kiro: Amazon's New Agentic IDE

Rain Clouds • 311 implied HN points • 14 Jul 25
đź•ą Technology AI Tools
  1. Kiro is a new IDE that can improve productivity by letting you focus on high-level planning instead of writing code. You describe what you want, and Kiro helps execute the project.
  2. Using Kiro requires creating clear specifications and being detailed in your instructions for it to work effectively. The better you articulate your needs, the better the results you'll get.
  3. Kiro is not perfect and has its limitations. It's key to know when to let it run on its own and when to step in and help it with specific problems or decisions.

Storytellers need video. Hypernatural makes it personal.

The Hypernatural Blog • 39 implied HN points • 23 Jul 24
đź•ą Technology AI Tools
  1. Hypernatural is a fast AI video generator that helps storytellers turn ideas into videos quickly. It makes it easy for writers and podcasters to create engaging video content without needing video editing skills.
  2. The software allows users to generate videos of any length and keeps character features consistent across different scenes. This means creators can focus on storytelling while Hypernatural handles the visuals.
  3. Hypernatural aims to expand creative opportunities for everyone, not just those who can afford professional video production. It empowers more people to share their creative visions through video.