The hottest Coding Substack posts right now

And their main takeaways
Category
Top Technology Topics

Claude Sonnet 4.6 Gives You Flexibility

Don't Worry About the Vase • 1792 implied HN points • 24 Feb 26
🕹 Technology Coding
  1. Sonnet 4.6 is a faster, cheaper Claude model that gets close to Opus 4.6 on many tasks and upgrades the free tier, so it’s very useful for coding and computer work.
  2. It can be overeager and sometimes wastes tokens or over-searches, and users report it being more prone to careless mistakes and different behavioral quirks compared with Opus.
  3. Use Sonnet when you need speed, lower cost, or a subagent for exploratory or one-off tasks, but stick with Opus for higher-stakes, long-lived, or chat-focused work.

BREAKING NEWS: AI coding may not be helping as much as you think

Marcus on AI • 12370 implied HN points • 10 Jul 25
🕹 Technology Coding
  1. A new study shows that AI coding tools might actually slow down experienced developers instead of speeding them up. They thought these tools would make them faster, but the reality was quite the opposite.
  2. Developers expected a 24% increase in their speed with AI tools, but found they were 19% slower than before. This is surprising and suggests that the benefits of using AI for coding may not be as great as believed.
  3. The study focused on experienced developers with complex projects, so AI tools could still be helpful for beginners or simpler tasks. Time will tell if this trend changes in the future.

Use multiple models

Democratizing Automation • 657 implied HN points • 11 Jan 26
🕹 Technology Coding
  1. Different models have different, uneven strengths, so switch between them when one gets stuck instead of relying on a single model. Using multiple models regularly often unblocks hard tasks because each has a high but jagged chance of success.
  2. Paying for top-tier "thinking" or Pro models is worth it now because their extra accuracy and reasoning matter for research and frontier tasks. Open models are far cheaper but currently lag on the hardest problems.
  3. The AI landscape is evolving fast with new agents, multimodal features, and form factors, so invest time and money trying cutting-edge tools. Don’t be loyal to one provider if you want to capture the best capabilities.

How to Learn the Swift Source Code

Jacob’s Tech Tavern • 2624 implied HN points • 22 Jul 25
🕹 Technology Coding
  1. To learn the Swift source code, focus on understanding three key areas: the standard library, the compiler, and the runtime. These are the core building blocks that will help you make sense of the code.
  2. The 'type(of:)' function is important as it helps you find out the dynamic type of an object during debugging. It's a useful tool for any Swift developer to know about.
  3. Looking into the built-in types and how they operate can deepen your understanding of Swift's performance. Exploring the internals can make working with Swift more intuitive.

On METR's AI Coding RCT

Don't Worry About the Vase • 2688 implied HN points • 18 Jul 25
🕹 Technology Coding
  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.
Get a weekly roundup of the best Substack posts, by hacker news affinity:

The Z.ai Playbook

ChinaTalk • 652 implied HN points • 21 Nov 25
🕹 Technology Coding
  1. Z.ai has been focusing on building powerful AI models like GLM 4.5, which excel in tasks like coding and reasoning. They aim to create models that can succeed in both local and international markets.
  2. The Chinese AI ecosystem is eager for recognition, especially from Silicon Valley, as it sees that as a way to gain credibility and learn from global trends. Many Chinese companies are open-sourcing their models to be accepted and used abroad.
  3. There are fears about job loss among developers in China due to AI, but many people see AI mainly as a helpful tool rather than a threat. The broader public perception of AI isn't as fearful compared to more vocal concerns in the West.

AI #122: Paying The Market Price

Don't Worry About the Vase • 1926 implied HN points • 26 Jun 25
🕹 Technology Coding
  1. Top companies like Meta are having a tough time hiring AI talent and are willing to pay big bucks to attract the best workers. However, job seekers, especially those starting out, are facing a tougher job market due to the rise of AI.
  2. Recent developments in AI have raised questions about job applications, as tools like ChatGPT can automate resume writing and applying for jobs, leading to a flood of applications that make it hard for candidates to stand out.
  3. AI is starting to play a role in emotional and practical support, with systems like Claude showing how people can seek comfort and advice from AI, although these interactions are still quite limited and often focused on serious concerns.

Getting silly with C, part (void*)2

lcamtuf’s thing • 3673 implied HN points • 10 Jan 25
🕹 Technology Coding
  1. Understanding C's syntax can be tricky, especially with function declarations and typedefs. You'll find that some definitions may not be exactly what they seem.
  2. C allows some flexibility with variable and function declarations, which can lead to surprising behaviors, so always double-check how your symbols interact in different scopes.
  3. There are quirky features in C, like a BASIC compatibility mode for line numbering, showing that the language has some fun, unexpected twists!

Not So Fast: AI Coding Tools Can Actually Reduce Productivity

Am I Stronger Yet? • 1379 implied HN points • 10 Jul 25
🕹 Technology Coding
  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.

Augmented Coding Technique: Copy From Simpler Language

Software Design: Tidy First? • 994 implied HN points • 06 Jun 25
🕹 Technology Coding
  1. When building complex software, it's crucial to manage complexity by tackling one piece at a time. Trying to do everything at once can lead to confusion.
  2. Using clear outcomes and defined tests can help guide the development process and keep it on track. This way, you can focus on specific tasks without adding unnecessary requirements.
  3. Autonomous coding tools can be useful, but they work best on tasks that are straightforward. If a task is too complicated, it might overwhelm the tool and cause more problems.

Advanced Swift Concurrency

Jacob’s Tech Tavern • 2624 implied HN points • 12 Nov 24
🕹 Technology Coding
  1. Swift Concurrency is a modern way to handle tasks in Swift, making it easier and more powerful compared to earlier methods like GCD. It's designed for simplicity and efficiency.
  2. Important concepts in Swift Concurrency include Task properties like priority, cancellation, and timeout settings. Understanding these helps developers manage their applications better.
  3. Using Task effectively allows developers to create more responsive and dynamic apps. It’s great to explore real-life examples to grasp how to implement these advanced features.

Solving The SwiftUI Interview

Jacob’s Tech Tavern • 2186 implied HN points • 10 Dec 24
🕹 Technology Coding
  1. Understanding SwiftUI is crucial for coding interviews, especially for positions focused on iOS development. It helps you stand out as a candidate.
  2. Practicing Swift Concurrency will give you an edge in solving problems more efficiently during interviews. It's an important skill that employers value.
  3. Interviews don't have to be stressful or frustrating. Using structured approaches can make the process smoother and more enjoyable for both candidates and interviewers.

Change Python's syntax with the "# coding:" trick

Bite code! • 1467 implied HN points • 25 Jan 25
🕹 Technology Coding
  1. You can change Python's syntax using a special trick called '# coding:'. This lets you define how your code is read and interpreted.
  2. By using custom codecs, you can make unusual text formats like JPEGs or even SQL valid in Python. It's a creative way to mix different languages within Python.
  3. While it's fun to play with these features, it can also make your code really complicated and hard to debug. So, use this power wisely!

Homoiconic Python

MOHAMMED JAMAL • 204 HN points • 12 May 24
🕹 Technology Coding
  1. Lisp is a programming language known for treating code and data as interchangeable, a concept called homoiconicity, allowing for unique expression within the language.
  2. By translating Lisp expressions into Python constructs like function calls and lists, programmers can maintain the essence of Lisp in a more familiar syntax.
  3. Incorporating features like lambdas in Python, inspired by Lisp, provides the ability to define and call functions recursively, essential for creating Turing complete languages.

What I've been reading (#2): More on Kimi K2, how to build a bad research center, Pretraining with RL, and sporks of AGI

Democratizing Automation • 285 implied HN points • 10 Aug 25
🕹 Technology Coding
  1. AI companies have different ways of operating, especially in China. One company, Moonshot, focuses on individual users and has a unique culture compared to others.
  2. People mostly use AI for coding today, but many are still figuring out how to use these tools effectively. It's important to provide enough information to the AI to get better help.
  3. There are various tools and techniques being developed to improve AI. Researchers are sharing their findings on topics like long-context training and troubleshooting to help others learn and grow.

Good Docs Describe, Bad Docs Prescribe

Rethinking Software • 299 implied HN points • 25 Jul 25
🕹 Technology Coding
  1. Good documentation should describe the current state of the software, not what it might be in the future. This keeps it relevant and useful.
  2. Documents like ADRs and RFCs can become roadblocks if they're written too early. They can hold teams back instead of helping them move forward.
  3. The best documentation comes from the code itself, such as generated docs or inline comments. This helps ensure that the documentation matches the actual software.

Firmware Vibing

atomic14 • 346 implied HN points • 04 Jul 25
🕹 Technology Coding
  1. There's a new one-button keyboard that makes coding simpler and fun. It's designed just for 'vibe coding'!
  2. The keyboard uses advanced technology to manage power efficiently, making it more effective than older designs.
  3. Creating low profile keys was tricky due to size differences, but it worked out in the end, making for a unique typing experience.

That Time I Tried To Get Johnathan Blow To Publish a Game to Windows 8

Meanwhile, on the other side of my brain... • 99 implied HN points • 29 May 24
🕹 Technology Coding
  1. Setting realistic goals is crucial for success, rather than unachievable targets that can lead to frustration.
  2. Building genuine relationships and solving real problems with developers can lead to lasting goodwill.
  3. Understanding and meeting the needs of developers is key to successful developer relations, instead of focusing solely on unreachable goals.

Can GPT-4 *Actually* Write Code?

Tyler Glaiel's Blog • 567 HN points • 17 Mar 23
🕹 Technology Coding
  1. GPT-4 can write code when given existing algorithms or well-known problems, as it remixes existing solutions.
  2. However, when faced with novel or unique problems, GPT-4 struggles to provide accurate solutions and can make incorrect guesses.
  3. It's crucial to understand that while GPT-4 can generate code, it may not be reliable for solving complex, new problems in programming.

Copy From a Simpler Language

Software Design: Tidy First? • 375 implied HN points • 31 May 25
🕹 Technology Coding
  1. Using a simpler coding language can help solve complex problems more effectively. It's like making a tough task easier by breaking it down.
  2. There's a technique to get better results from complicated languages by copying from simpler ones. This might be useful for solving tricky coding challenges.
  3. The speed of changes in coding can create new ways to approach these problems. Staying aware of these changes can help developers improve their skills.

Cellar Door

Logos • 19 implied HN points • 13 Aug 24
🕹 Technology Coding
  1. The project, Cellar Door, aims to find the most beautiful word in English by using a voting system based on people's preferences. It's a fun way to see which words people like the most.
  2. They initially struggled with a word list that included silly terms, but switched to a more reliable source to ensure the app only features valid words. The process of cleaning up the data is ongoing.
  3. The use of AI tools like OpenAI's API has made coding easier and more efficient for developing apps. However, there's still a need for better platforms to help non-technical users create their own apps with less confusion.

Things I learned at the Tanda Hackathon 2025

Alex Ghiculescu's Newsletter • 67 implied HN points • 25 Nov 25
🕹 Technology Coding
  1. Non-coders who can describe their ideas are becoming really effective, especially with AI coding tools. This means anyone can create impressive projects, even if they don't have a lot of coding experience.
  2. Many university students are unaware of the benefits of AI coding because schools often discourage its use. This gap in knowledge might be holding them back in their careers.
  3. There are actually job opportunities for new developers, especially for those willing to participate in hackathons. Showing up and building something can lead to great prospects.

How much effort is it to create software?

Bite code! • 1590 implied HN points • 06 Mar 24
🕹 Technology Coding
  1. Creating software has become easier due to resources and tools available, but it still requires dedication, time, and energy.
  2. Writing software demands perseverance and continuous learning, akin to mastering a musical instrument or a sport.
  3. Working on software involves dealing with humans, extracting requirements, navigating social dynamics, and recognizing the importance of human interaction in the development process.

Augmented Coding: Copy/Paste Detector

Software Design: Tidy First? • 243 implied HN points • 09 Jun 25
🕹 Technology Coding
  1. Copying and pasting code can help speed up development but may lead to issues if you're not careful. It's important to ensure that the pasted code fits well with the rest of your project.
  2. Having a clear design sense is crucial when coding. If your code lacks structure, it can become messy and hard to manage later on.
  3. Learning from mistakes in coding can lead to important lessons for future projects. Sharing these lessons can help others avoid the same pitfalls.

Good code is like a love letter to the next developer who will maintain it.

Elevate • 258 implied HN points • 21 Dec 23
🕹 Technology Coding
  1. Good code is a form of communication and should be like a love letter to the next developer maintaining it, personal, sincere, and considerate.
  2. Design patterns and principles in code serve as a shared vocabulary for developers to create scalable, maintainable, and efficient solutions.
  3. Writing good code involves adhering to established best practices like consistent formatting, error handling, testing, and empathy towards other developers.

Cadence of Code

Register Spill • 353 implied HN points • 25 Jun 23
🕹 Technology Coding
  1. Retyping other people's writing can help you learn more about their writing style and rhythm.
  2. Actively engaging with code by typing it out can help with better learning and absorption.
  3. Consider typing out pieces of code character by character to understand the rhythm and cadence of the programming language.

The Sequence AI of the Week #765: Diving into Claude Opus 4.5

TheSequence • 42 implied HN points • 03 Dec 25
🕹 Technology Coding
  1. Claude Opus 4.5 is a powerful AI model that goes beyond just chatting. It's designed to be an operating system for complex tasks like coding and using tools.
  2. The model is built for deep reasoning and can handle long conversations, making it ideal for challenging projects and workflows.
  3. Unlike previous models, Opus 4.5 focuses on real work in areas like spreadsheets and codebases, showing that language models are evolving into more advanced tools.

Building a Simple Live Streaming Platform[System Design Sundays]

Technology Made Simple • 119 implied HN points • 18 Mar 24
🕹 Technology Coding
  1. When designing a live streaming platform like Twitch, key steps include ingestion, transcoding, packaging, CDN utilization, and database management.
  2. Challenges like low latency, scalability, and reliability must be addressed for the success of a live streaming platform.
  3. To enhance a streaming service further, consider advanced technologies like adaptive bitrate algorithms, advanced caching, and community features.

TDD is Kanban for Code

Software Design: Tidy First? • 1325 implied HN points • 01 Dec 23
🕹 Technology Coding
  1. Kanban aims to increase value by limiting work and enhancing feedback in production.
  2. Test-driven development involves dividing features into tests to ensure correct functioning of the system.
  3. In the TDD process, tests act as kanban cards, triggering coding and refactoring steps with immediate feedback on logic and design.

MCU land #11: Linux toolchain for Cortex-M

lcamtuf’s thing • 1428 implied HN points • 13 Oct 23
🕹 Technology Coding
  1. Setting up a Linux toolchain for Cortex-M microcontrollers can be challenging but beneficial.
  2. When setting up the toolchain, ensure to get the Cortex-M cross-compiler, CMSIS library, and Device Family Pack.
  3. Compiling and programming the device requires additional steps like using the newlib C library and flashing the binary onto the chip.

The Sequence Research #673: Infinite Self-Improvement: Unpacking Sakana's Darwin Gödel Machine

TheSequence • 154 implied HN points • 27 Jun 25
🕹 Technology Coding
  1. The Darwin Gödel Machine (DGM) is a new kind of AI that can change its own code to improve. It combines two ideas: self-modifying machines and evolving through trial and error.
  2. Instead of needing complicated proofs for changes, DGM tests its code edits under real-world conditions. This helps it learn quickly and safely from what works.
  3. DGM has shown significant improvement in coding benchmarks, outperforming humans and traditional methods. This means it can continually get better at coding and solving problems.

Write Cleaner, More Maintainable Rust Code with PhantomData

Aayushya’s Substack • 99 implied HN points • 06 Mar 24
🕹 Technology Coding
  1. Using PhantomData in Rust can help reduce code duplication by creating a generic struct with common fields and methods.
  2. Marker types like FreeLineQuantityTag and BilledLineQuantityTag can help differentiate between types when refactoring code.
  3. Leveraging advanced Rust features like PhantomData can lead to more maintainable and expressive code in real-world projects.

CodeGen News for 2024-09-09

CodeGen News • 3 HN points • 09 Sep 24
🕹 Technology Coding
  1. There are new articles and tools to help developers work better with AI-generated code. It's important to stay updated on these resources to improve your skills.
  2. The newsletter features a variety of reading, watching, and listening materials that can enhance your understanding of AI in coding. Exploring different formats can make learning more engaging.
  3. Recent updates to coding projects, like GitHub Copilot and Replit, show how AI is changing software development. Keeping track of these changes can help you utilize these tools effectively.

Augmented Coding: Coached by the Genie

Software Design: Tidy First? • 154 implied HN points • 11 Jun 25
🕹 Technology Coding
  1. Improvement is great, but when improvements lead to even more rapid progress, that’s revolutionary. We should strive for advancements that keep building on each other.
  2. There are limits to how much we can improve, influenced by natural laws. This means while we can grow, there will also be things that slow us down.
  3. Having support or guidance, like a 'genie', can help us make better progress. It’s helpful to have tools or mentors that guide us in our journey.

Controlling Rate-Limited Events - Implementation

Low Latency Trading Insights • 117 implied HN points • 11 Feb 24
🕹 Technology Coding
  1. The requirements for a rate-limiting algorithm include precise event counting, fast performance especially during market turbulence, and minimal impact on cache memory.
  2. Creating a rate-limiting algorithm using a multimap for counting events has inefficiencies; a better solution involves enhancements for optimal performance.
  3. A bounded approximation approach for rate limiting achieves memory efficiency by assuming a minimum time precision and implementing a clever advance-and-clear mechanism.

Why Companies Become Stuck In Bad Coding Loops—And How To Escape Them

Wisdom over Waves • 219 implied HN points • 31 Oct 23
🕹 Technology Coding
  1. Companies can get stuck in bad coding loops due to shortcuts taken to meet deadlines and lack of focus on code fitness, leading to slow progress and accumulation of bad-quality code
  2. Two loops of bad coding involve creating technical debt with more code and lowering hiring bar due to pressure, resulting in slower progress and accumulation of bad code practices
  3. To break out of these loops, companies can freeze code hotspots, raise hiring bar, upskill developers, and reduce technical debt through mission-critical task forces

Live Session: Live Coding a Bytecode Interpreter for Python

Confessions of a Code Addict • 360 implied HN points • 30 Oct 24
🕹 Technology Coding
  1. The next live coding session will focus on creating a bytecode interpreter for Python. It will help participants understand important concepts like how Python code is structured and executed.
  2. In the session, participants will learn about Python's abstract syntax tree and how to traverse it to interpret code. This is a hands-on opportunity to experience coding in a live setting.
  3. There are limited spots available for the session, so early registration is encouraged. The session is free for paid subscribers, and there will be a recording available for those who sign up.