Pinned Tweet
intelligence is the one which removes suffering. If suffering is not removed it's not intelligence.
2
5
1,570
ATechieThought retweeted
Prefer reading to watching?
50 talks from AI Engineer Code Summit, now in writing: illustrated essays, full transcripts and links to watch.
Pick a topic. Find the idea you want to try.
ai.engineer/code/2026#talks
ATechieThought retweeted
the creativity behind this website is fu*king unreal
human-md.ai
ATechieThought retweeted
I just finished talks about my software factories at two conferences. Afterwards a bunch of people came up and told me what they were surprised about. Here is a distillation of what people thought were hot takes from my two talks.
First hot take: I tell everyone to slow down. Most speakers go on about how fast they're going, but I strongly believe in pacing AI outputs to human speeds. I regularly tell AI-pilled CIOs and CTOs to chill: almost nobody is _actually_ going fast with AI. Engineering still moves at engineering speeds, and business moves even slower. The ones pushing too hard are starting to see downtime for it.
If you don't pace your AI to human speeds, everything starts breaking around you, even at small operations like my online video game. I only have about a dozen humans working with my factory, and only a few hundred active old-timer players in the community who get along well, and still, introducing AI has still been very rocky.
My agents have, at times, overwhelmed my players with features, my accountant with emails, my merge queue with tickets, and my machines with load. Agents have pissed off my admins, resulting in name-calling, they've made messes in the game, and they've launched broken OSS without permission. The list goes on.
I can get away with all this chaos because everyone involved in my operation is very forgiving. They're excited by the potential. But even so, I had to learn to slow down, real fast. And so that's what I preach.
Hot take #2: Should you buy a software factory? Do you even need one? No. You probably don't need one. Factories take an extraordinary amount of upkeep. They turn into garbage mountains unless you put a frightening amount of time and tokens into curating them. I had to burn my previous five factories down since it eventually became cheaper to rewrite them than to fix them. So I'm not out there advocating for software factories or swarms just yet. If you do want one, be aware that it is a significant commitment of both money and human leadership to keep one running.
Several people told me that I was the only one who stood up onstage, at either conference, and said Build, don't Buy. But my experience is that software factories grow to be highly bespoke to your domain. Mine is super tangled up with my game, and I think that's inevitable. Because the factory is not just building my product, it's supporting it too. It's a company in a box. And they're easy for Claude to build for you.
Third and arguably hottest take: Next year will have a lot of human/agent and agent/agent office drama, resulting from bringing in AI employees, and it will be gloriously funny, but also frustrating.
Many of you are already on this bandwagon, but everyone next year will have a personal chief-of-staff agent. Busy people, even hobbyists, will have whole entourages of helper agents. The hot take is that people will become so dependent on these little private entourages, that they'll bring them to work. Your people will talk to my people, etc. Whole protocols will emerge for private entourages negotiating work between humans, inside companies big and small.
Nearly all humans will wind up having to start working with AI employees next year, and it'll be the beginning of the biggest cultural change we've seen in a hundred years.
So that's the hot takes. Slow down. Only build a factory if you think you really need one. And focus on empowering yourself with your own agentic chief of staff (or team). Your entourage will define how you work with others, so start by perfecting how you work with them yourself.
Great advice, Love these “We don’t need to predict the answer. We need to manage risk while the market figures it out.”
A follow-through day is a reason to get more engaged, not a reason to throw caution out the window. This may be a day to test small, or not at all”
A Follow-Through Day?
Today could be a follow-through day. That’s usually when we start looking for opportunities to put money to work.
But there’s a catch. The gap is being driven by semiconductors, still one of the weaker groups, following a strong $CRWV report. Meanwhile, most of our setups are in medical and healthcare, and that group is red this morning.
Half of all follow-through days fail. Watch @mwebster1971 videos on FTD's, that's your homework!
Here’s the question I’d keep in mind: Where do you think we’ll be one week from today? In a full-blown, glorious uptrend, or still dealing with chop, failed breakouts, and uneven leadership?
We don’t need to predict the answer. We need to manage risk while the market figures it out.
A follow-through day is a reason to get more engaged, not a reason to throw caution out the window. This may be a day to test small, or not at all.
Let the quality of the setups and the market’s follow-through determine how much exposure we earn.
1
30
Read the blue book and then red book for DDD. It’s been ages know to the best folks, broken orgs are finding it as innovative thing now. Glad that Matt is highlighting it again.
As expected, the thing that is blowing people's minds most in my course is not the agentic stuff.
It's the DDD stuff - domain-driven design.
Building a ubiquitous language, using it with the agent, and refactoring the code to use it.
Just bonkers how good it is
37
I correlate the term more to factory as object design pattern than historical usage of software factory term. This way my mental model don’t get corrupted or I don’t see I am doing something special. Meta programming was good name but again has baggage.
Just wanted to defend the term "Software Factory" for a second.
First, the caveats:
It's bullshit. It sounds fancier than it really is.
It's a bandwagon. People are using it to get you and their VC's hyped.
But it's also referring to a real change.
Earlier this year, most SOTA teams were using agents to work on the product. Shipping features, fixing bugs.
But now, they're building automations to help agents work on the product for them. They've moved up a layer.
What do we call the thing they're building? Loops? Workflows? Some other generic label?
"Software Factory" is as good a term as any other.
- "We're not working on the product, we're working on the factory that builds the product."
- "We're not product engineers, we're factory engineers."
I like it. I'll continue using it.
33
ATechieThought retweeted
[new blog post]
Writing as a thinking tool
muratbuffalo.blogspot.com/20…
I’m dreaming of autodream!
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
28
Building code review agent yourself is surely wrong path unless you’re in business of dev tools or in very very large org platform team. Decide what is your core business.
Alright, it's time to address the code review bottleneck.
Here's 3 steps worth adding to your agent workflows:
1. Build your own code review loop
2. Verify flows end-to-end with simulated environments
3. Score and mitigate risk with /merge-risk
1
50
ATechieThought retweeted
This is 100% true.
Your reliability in general should be *higher* with agent written code, as measured by error rates, SLO violations, client regressions etc.
If you’re having more or equal incidents now than when you were manually writing code, that’s likely a “skill issue”.
Replying to @thorstenball
Agreed. We have shockingly few production errors these days. E.g. panic from a missing nil-check happens once every couple of months, and usually involves legacy code humans partially wrote. At this point, if I write it by hand you are going to get more bugs.
ATechieThought retweeted
This is a great and much needed public service. Thank you Cloudflare!
Introducing Zero Wire: a public vulnerability intelligence feed on @CloudflareRadar, bringing the clarity of a news wire service to critical security developments. cfl.re/4iCvSbj
ATechieThought retweeted
It's been a rough few weeks for security.
I pulled together a guide of the highest-impact actions you can take today:
ATechieThought retweeted
It’s with a very heavy heart that I pass along some gut wrenching news💔💔
The trading community lost a GIANT of a man Oct 31st
Please send your love & positive thoughts to @TaPlot’s family💔🙏
WRO #64 Because We Never Give Up, Hangin' Out with TA Plot youtu.be/zEOlhcW9xE0?is=mssl… via @YouTube
this is basically the bitter lesson at work
the smartest models will need fewer and fewer tokens, they won't need to verify their work or check it for bugs, they will just be right
maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether
i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis























