Craig Rowe

Coder, Blogger, Atheist, Self-Labeller.

[Eduardo @hackerdocc]

this is honestly infuriating. if you blindly forward AI answers to people it's a signal you are dumb, which is fine there's nothing wrong with it, the problem is that it also shows them you think _they_ are dumb, in one of the most offensive ways possible

[Addy Osmani @addyosmani]

"Cognitive surrender is when you stop thinking altogether and blindly accept the answer the AI gives you"

[Addy Osmani @addyosmani]

https://t.co/jKCIAEzai7

[Craig Rowe @cargowire]

Remember guys when smashing out stuff with AI, as Ian Malcolm would say "Your scientists were so preoccupied with whether or not they could, they didn’t stop to think if they should."

[Sergio Pereira @SergioRocks]

I used to think I was a fast Engineers because I could code quickly.

Open the editor, start building, figure things out along the way.

That’s how most of us learned. And to be fair, it worked.

But looking back, most of the time I wasn’t really building.

I was discovering:
- What the system should do
- What edge cases existed
- What the real requirements were

And I was doing that while writing code.

But now with AI, that approach breaks.

Because now code is cheap. What’s expensive is ambiguity.

So I changed my workflow completely:
- I spend more time on the spec than on the code
- I define behavior before implementation
- I use AI to generate the code
- I test against the spec I defined

The result is not just faster. It’s more reliable and deterministic.

I wrote a full breakdown of this in my latest newsletter:
https://t.co/j5Zbi3W5jh

[Cassidy @cassidoo]

idk how else to say this, but... build your dream projects now.

I feel like all the tools are giving away a LOT for free/cheap now. It's only gotten more pricey over time, and will keep getting more expensive. Your ideas are subsidized now, think of it as a fire sale and build!

[Gergely Orosz @GergelyOrosz]

There is massive irony in how AI coding tools are starting to become TOO expensive for many enterprises - after eg Anthropic removed subsidizing AI subscriptions.

We might go from "everyone use AI for everything!" to "you have $300/month AI budget; use your brain for the rest."

[Heather Downing @quorralyne]

I've been optimizing tokens for most of the year now. Compute isn't free, and companies will start looking at budgets against their ROI eventually.

[Craig Rowe @cargowire]

😂

[Miguel de Icaza ᯅ🍉 @migueldeicaza]

People are out there writing Claude skills, and here I am giving instructions with typos and not even naming types or classes “that type that stores the bindings”

[Lenny Rachitsky @lennysan]

"Using coding agents well is taking every inch of my 25 years of experience as a software engineer, and it is mentally exhausting.

I can fire up four agents in parallel and have them work on four different problems, and by 11am I am wiped out for the day.

There is a limit on human cognition. Even if you're not reviewing everything they're doing, how much you can hold in your head at one time. There's a sort of personal skill that we have to learn, which is finding our new limits. What is a responsible way for us to not burn out, and for us to use the time that we have?" @simonw

[Work Chronicles @_workchronicles]

(comic) Evaluating Trade-offs

[Simon Willison @simonw]

@mempirate @AmpCode Coding agents can't take accountability for their mistakes

Eventually you want someone who's job is on the line to be making decisions about things as important as securing the system

[Craig Rowe @cargowire]

One of my strongest memories as a kid was staying up late to watch Red Dwarf on my tiny TV. Iconic show with a lead who shared my name and a secret you could reveal that 'Grant Naylor' wasn't one person it was two.

[Craig Charles @CCfunkandsoul]

Earlier today I was informed of the passing of @realrobgrant .i am in total shock.He was one of the funniest people I’ve ever met. A visionary.
My heart goes out to his family and friends. The impact he and Doug had on the course of my life is immeasurable
RIP ROB

[Simon Willison @simonw]

This stunt feels irresponsible to me. If we don't want regular people developing toxic relationships with their chatbots it really doesn't help for leading labs to start giving them "retirement interviews" and encouraging them to blog their "musings and reflections"

[Andrej Karpathy @karpathy]

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.

Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.

As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now.

It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

[Craig Rowe @cargowire]

Kinda funny seeing this after essentially spending a week or so doing this manually 😂

[Aseem Shrey @AseemShrey]

I made Claude and Codex argue until my code plan was actually good.

⚡️ Built a Claude Code skill where Codex reviews Claude's plans. They go back-and-forth until Codex approves.

🎯 3 rounds. 14 issues caught. Zero manual review.

Skill & Blog : https://t.co/xBaf2v2oMs

[Adam @adamdotdev]

I find it very funny when anyone feels confident that they've figured out agentic programming, even funnier when they're trying to teach others how to do it. I've been working on OpenCode since May of last year and I still have days (like yesterday) where I'm not even sure any of this is a good idea lol

I end up landing on "yes, these models are an incredible tool" but it's still all very confusing, lots of tangled thoughts and emotions and realities.

I badly miss the mundane coding tasks that broke up my days/weeks, the ones where you put on the headphones and just bang out 600 lines of code. But, no question, replacing those hours of my time with a few minutes of waiting on an agent is a boost and worth being excited about, despite the mixed emotions.

Then there's the distance that can creep in between you and the codebase if you start getting apathetic. I think it's pretty common at this point to make even small changes by prompting the models. It's less friction than finding the relevant code and making the change yourself. And less friction seems to win, must be some law of the universe or some shit. When most or all of your interactions with a codebase start flowing through the models, you start to lose track of where things live, which abstractions/components are carrying the weight, etc. It's a scary feeling to wake up and realizing you can't even reliably @<mention> a precise file for a change you want to make, and you have to get more vague, leaning harder on the model.

It all creeps up on you, there's an undeniable dopamine hit from using these things, and the resulting come down is predictable, like coming off a sugar high. On the positive side, it's really nice seeing other devs go through the same cycles, knowing we're all in this together and we'll ultimately figure it out.

[John Crickett @johncrickett]

Software engineers: Context switching kills productivity.

Also software engineers: I'm now managing 19 AI agents and doing 1800 commits a day.

We’ve spent years complaining that managers who expect a quick 5-minute chat ruin our focus for the next hour. But a ping from an agent every few minutes, that’s ok?

We celebrated Paul Graham’s essay “Maker’s Schedule, Manager’s Schedule” in which he argued:

“When you're operating on the maker's schedule, meetings are a disaster. A single meeting can blow a whole afternoon, by breaking it into two pieces each too small to do anything hard in.”

Now we see software engineers claiming huge productivity gains from hordes of AI agents, celebrating thousands of commits per day from their 19 agents.

Either context switching was never really the problem, and we oversold our need for deep focus. Or we're not actually reviewing 1800 commits a day.

If we couldn't context switch before, we're not managing 19 agents. We're blindly trusting them.

That’s not engineering, it’s gambling.

[Craig Rowe @cargowire]

"You're right, I was wrong. Let me correct myself."

The trouble sometimes with AI.. when do you stop a back and forth and assume that the truth has been found (assuming being the operative word if you aren't manually checking)

[Craig Rowe @cargowire]

😂

[Martin Adams | Building Flowtelic @Martin_Adams]

The new productivity buzzkill...