Balint Erdi

The "How to Become an Effective Software Engineer" book is out 🎉 The traits, tips and tricks I've collected in 25 years as a software engineer, distilled🦉 Please share this to reach more developers early in their careers. Thank you ❤️ effective-software-engineering.com

⚠️ AI agent skills are becoming a new attack surface and most teams aren’t prepared. In OpenClaw, “skills” are treated as documentation, but in reality, they can act as installers. And attackers are already exploiting that. @jmeller, VP & Security Strategist @1Password, found that a top-downloaded skill in a popular registry was being used to deliver macOS infostealing malware. This is why the future of agentic AI needs identity and access controls that are time-bound, revocable, and attributable. Must-read 👉 bit.ly/3OkmCgn #AIsecurity #AgenticAI #CyberSecurity #IdentitySecurity #1Password

Sign up here to get a sample: effective-software-engineering.com

A small excerpt from my upcoming book, "How to Become an Effective Software Engineer". See link in the comments below.

@bcherny @nicmeriano @karpathy Can you say more about how you use Claude Code to suggest refactorings (or find possible issues) on opened PRs? Thank you.

@nicmeriano @karpathy Yep here’s an example. /dedupe skill invoked on every issue github.com/anthropics/cla…

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

I'm happy to report that The How to Become an Effective Software Engineer book now has a landing page, and you can download a very generous sample: effective-software-engineering.com

The "How To Become an Effective Software Engineer" book is coming along nicely, and should be out this year. Sign up here: fullstack-consulting-llc.kit.com/72aa1e93d9

I must have spent days of my life typing `document.querySelector(All)` in browser consoles only to realize I can simply type `$(selector)` and `$$(selector)`

Part 2 of the Teamtailor Embroider series goes through all the things we did to make static invocation possible in our large Ember app. I hope you enjoy reading it and that you might learn something you can apply. career.teamtailor.com/posts/our-jour…

We just published the first blog post in a series on how we switched to Embroider at Teamtailor, and the huge dividends it paid: career.teamtailor.com/posts/our-jour…

Such a great article on LessWrong (and one of the few ones I mostly understand 😅) about why ChatGPT is a sycophant. lesswrong.com/posts/2pkNCvBt…

Here’s the full lineup for this edition of Ember Europe: starting off with our @real_ate , then @davidtaylorhq , and Linds McElroy; followed by open Q&A. It’s happening on July 3 at 19:00 CEST. Don’t let it slip through your fingers. RSVP details down here 👇🏼

We're giving away 3 on-site tickets in our scholarship program. If you contributed to Ember (through code, documentation, community support, etc.) and would benefit from financial help to attend, please write a message to mail@emberfest.eu The deadline is July 5th 00:00 CEST.

Stoked to announce two more speakers: Krystan Huffmenne is a member of the Ember Data and TypeScript core teams. Preston Sego (@nullvoxpopuli) is an author and contributor to several add-ons and a member of the Ember Tooling core team. Join us: emberfest.eu

@JeffreyBiles Nice! What was the prompt?

Today we celebrate the 111th birthday of Norman Borlaug. The man who fed the world. Borlaug developed high-yield, disease-resistant wheat that sparked the Green Revolution, saving over a billion lives from hunger. Happy Birthday, Norman Borlaug - hero of humanity.

HomeExchange is one of the services I use and recommend wholeheartedly I've been able to travel with my family to others' homes and save a lot of money on accommodation. Not to mention you stay at a nice home with all its benefits instead of hotel rooms. homeexchange.com/?sponsorkey=pe…

It occurred to me that I couldn't exactly define what arrogance is. I then came up with this: one is arrogant insofar as they think the only way to do something (or the only way to think about something) is the way they do it. Is this a good definition?

Here is rule #13 from the tentative "How To Become an Effective Software Engineer" book. I learned a ton from pair programming and have had a lot of fun, too: devjournal.balinterdi.com/do-pair-progra…

This one was above-average hard to write but it's probably one of the most important rules. I have the impression soft skills are underrated in lots of engineering organizations, even though communication is a killer soft-skill to wield. devjournal.balinterdi.com/improve-your-c…