I’ve found that agents are great at debugging any problem when provided with this two-tier framework for troubleshooting. This requires enforcing discipline and imposing constraints, rather than give agents a free rein or vague end goals, but works better than unguided “loops”.

Today @bitdriftio is really excited to open source blob-stream: a Kafka alternative for no fuss, low cost high volume streaming. I wrote in depth about what blob-stream is, why I made it, and how I made it. blog.bitdrift.io/post/blob-s…

People talk about the diminishing returns of writing unit tests in the agentic era, but what’s even less useful? Comments. As a rule, drop all comments. If something is important enough to need a comment, make an exception for it and audit the comment so it actually makes sense.

I need a personal agent for work where it: - triages all incoming bugs - manages slack comms - gives me a summary and classification of all emails (8000+ unread), design docs, SEVs etc I don’t need an agent for my personal life, where I just don’t deal with anything like this.

Here’s an example where Twitter Engineering was way ahead of the curve. Many companies didn’t have to deal with “Twitter scale”, but agentic architectures are fast changing the scale even small orgs are expected to handle re stateful load balancing, orchestration, storage etc.

Ball-knowers knew all along that Twitter wasn’t just going to collapse after Elon fired 75% of the staff, because Twitter 1.0 had some of the best infrastructure engineers working on it, and when you get that calibre of people building your foundations, it lasts.

With agentic coding, even in the best case scenarios (where you read every line of generated code), there’s something we’ve lost, perhaps irrevocably. That has a real cost, & not to mention, second and third order effects, that “software factories” etc don’t necessarily solve.

Writing a post about “how to effectively debug code when you no longer fully understand it”. This is real bug I had to fix in ~9K LOC (100% AI generated). None of the tactics I started with here helped “root cause” the issue, lol. Had to take a different approach to isolate it.

One thing I don’t see many talk about is how coding agents can often *amplify* weaknesses, both individual and organizational. I think of this as the “empty calories” problem, which is exacerbated when “hyperproductivity” originates from your team’s “lowest common denominator”.

The IDE/editor might be dead, but it helps to occasionally open one and read some code. Often, what “looked OK” in isolation when an agent wrote a patch can end up looking *very* different from more of a “panoramic view”, with misshapen and incoherent APIs, abstractions.

The people who blithely claim “you don’t need to understand the code anymore” aren’t telling you what debugging looks like in such cases Here’s one example where I had to debug a gnarly problem at work with Claude *without* access to the code Possible? Yes “Easy”? Nope 🙂‍↔️

I’m increasingly convinced that “giving a shit” will be a competitive differentiator now that everyone is using AI to do their work. Ten years ago, I had this manager who was a perfectionist. whenever he thought a presentation was “done” he’d spend 15 more minutes changing colors and aligning shapes (that were def already aligned, btw) and checking where the titles sat so they didn’t jump from slide to slide. He was purposefully trying to locate the point others would quit, and then put just a little more effort in. At first I was like dude you’re a psychopath we’ve been working on this deck for a month. It’s great. But his point was that going the extra 10% has a non linear impact if everyone else stops at around the same point. That was pre AI. Today people can pump and dump drivel at a fantastic clip. And they hit send or post after pretty minimal effort, awash in the glory of the 80% ok slop they so quickly created. On one hand, it’s frustrating. But on the other hand, it’s creating a new opportunity to stand out by simply giving a shit. By caring about your work product a little bit more and taking it personally you separate yourself by a wide margin. So give a shit today! It might make you great.

Never become a mindless shill for your employer on social media. Jobs come and go. Your credibility, integrity, reputation, and not to mention, self-respect are for the ages. And some people have long memories.

August farmer’s markets in the Bay Area are worth a visit just for the abundance of fresh, juicy figs, and in-season tomatoes. 🍅 Refrigerated, slightly overripe figs make for the best dessert, IMO.

adopted ASD-STE100 in my project upon a coworker’s recommendation. Asking Opus 5 to write comments/commit messages etc in plain English has more benefits than just helping with readability. It discovers bugs. Critical bugs.😱 I was absolutely gobsmacked after seeing this. Wtf!

I remember how much effort it took to commit some commands to muscle memory (tcpdump, lsof, nc, openssl, strace etc), and even then just a limited set of these. and now to see agents blaze through a debugging session conjuring commands and spellings I didn’t even know existed 🤯

In recent weeks, when it came to tricky bugs (a memory leak, a routing issue, a sharding bug), Claude’s initial analysis was almost always 100% wrong. I had to give it multiple hypotheses, clues, ideas, suggestions for it to solve the bug. When asked “so, what did you learn?”

New blog post! "Lorenz and Little: How Much Does Your Tail Cost?" takes a look at how much tail latency contributes to the concurrency in a system, and how much that contributes to cost. brooker.co.za/blog/2026/07/2…