John (@johnblythe) header
John (@johnblythe) profile picture

Building https://teapaw.org/t.co/78ySskQkMy, https://teapaw.org/t.co/aJwaCiGcqG, and teams @Launchdarkly. prev: @datavantHQ, @curvolabs, @kyruus, CombinedCuriosity, @heysequense. views are great + my own

Indianapolis, IN
Joined June 2007
Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)Photo by John (@johnblythe)
John retweeted
Keeping up with AI and shipping your actual work can feel like 2 full-time jobs. At Every, we split those responsibilities. Our Frontier team tests new models and workflows, then shares what works with product teams who can stay focused on building. @danshipper: Give experimentation a home, then make its findings useful to everyone else. Watch the full Fable 5.2 camp: every.to/events/workshop-202…
2
2
1
21
2,816
.@poteto's talk at AIE Code is excellent. If I had to pick one still from that felt genuinely original, it would be this one: "nuance tends to lead to slop" To increase quality, design API's and automated checks that remove the nuance from agents' decisions. - Ban useEffect - Ban 99% of explanatory comments (they just lead to workarounds) - Create API's that hide complexity from agents Full talk below.
86
66
15
1,554
65,626
πŸ‘ πŸ‘
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.
1
49
looks like bumping to the claude ultra plan is becoming a holiday tradition for me. tis the season to cook. πŸš€
1
35
John retweeted
Obsessing over your skill stack is the new microservices
22
22
4
277
21,656
Agree! Except @LaunchDarkly ftw
This is how agents will ship all code. β†’ Agent writes feature-gated code β†’ Verification gates on push (proof checking, security audits) β†’ Agent monitors metrics You can live the future today with Vercel CLI: πšŸπšŽπš›πšŒπšŽπš• πšπš•πšŠπšπšœ, πšŸπšŽπš›πšŒπšŽπš• πš–πšŽπšπš›πš’πšŒπšœ, πšŸπšŽπš›πšŒπšŽπš• πšπšŽπš™πš•πš˜πš’.
27
AI interfaces nowadays are still pretty much turn-based. In my PhD thesis, I thought about what interaction would look like if we could go beyond taking turns. One example is intra-turn interaction:
300
609
216
8,464
782,678
Speaking at @aiDotEngineer Code Summit SF, the "software factory stack" seemed to resonate. Here's a breakdown of the components: 00 – Factories-as-code. Every aspect of the factory (agent workflows, access permissions, cloud sandbox configuration, and so on) should be version-controlled code that humans and agents can modify. 01 – Data & Context. You should own all of the data your agent interacts with on your own infrastructure. Your internal skills and MCPs, agent traces, access logs, telemetry... everything. 02 – Compute. Agents should have their own computer, with controlled sandbox permissions and support for multiple operating systems. This should be self-hostable. 03 – Inference. You should have access to any model and any harness to benchmark the right match for your setup. Don't lock in to any one model provider. 04 – Improvement. You (and agents) need tools to measure and improve your factory. This means observability over cost-per-PR, cycle times, latency, and other DORA metrics. It also means self-improvement, with agents scoring output quality, proposing changes to the factory, and re-measuring in a loop. 05 – Orchestration. You need a runtime to launch agents, track work, and recover from failures. It should also handle message passing between agents in a multi-agent system. 06 – Access. You should be able to connect the factory to any external system. You'll want an MCP server and REST API to access the factory itself, and integrations with where your team works (Slack, MS Teams, Jira, Linear, etc). We don't recommend an "ADE" or web interface that's tightly coupled to the factory.
33
24
4
299
31,326
John retweeted
the thing the majority of people will never understand is once you create an asset it basically can't lose a mediocre person can run it and it'll just keep growing. you can even see this at small scale, a lot of "famous" employees just joined companies at the right time what's totally invisible is the path not taken. great founders will rebuild the asset over the decades into something else it's very hard for a hired ceo to ever do this
Replying to @naval
Apple's market cap under Tim Cook went from less than $350 billion when he took over for the late Steve Jobs, no doubt a brilliant visionary, to $4.6 trillion. Sadly, we are all replaceable.
55
51
10
1,345
70,227
Wondering how @dhh and @jasonfried have calibrated shape up pods with agents now involved. I’d guess it was the most stable and least disrupted WoW, but could have some interesting new optimizations.
30
"The more secrets you have, the less happy you’re going to be." @naval
20
88
6
1,231
77,926
PSA: creating wonderful products still requires extraordinary amounts of human focus, effort, motivation, and love. And an attention span.
341
513
105
4,597
148,577
opus 5.5 is markedly dumb today. thanks fable πŸ™„
1
2
120
Here's my take on what a software factory really is This is my talk from @aiDotEngineer NYC, and I decided to record a version for everyone to watch on X. tl;dr - software engineering is becoming factory engineering, and there's new work (especially factory benchmarking) that engineers should start focusing on.
37
89
18
1,057
861,845
Agreed. Been a weird hotness lately that doesn’t quite square
it's crazy to me people still argue about subagents most of our team tells opencode to do everything in subagents it's also how we're drastically cutting costs and still getting reviews from expensive models
39
John retweeted
when we can do anything, do we still know what we want? the full talk from @aiDotEngineer shanghai. every slide handmade in keynote, subs in δΈ­ζ–‡ and english
67
164
47
1,371
88,780
This. Making software is cheap. Owning software is not.
I think we’ll see a lot more of this in the coming months Companies replacing saas products with internal tools or self hosted open source alternatives But building software is one thing… maintaining it is another And honestly, cybersecurity is my biggest concern here Just look at the AI attacks we’ve seen in recent weeks. Now imagine thousands of companies running their own infrastructure, with outdated dependencies, security holes, and nobody keeping an eye on things Sooner or later, they’ll realize they need entire teams just to keep these systems running and secure Then comes the decision, go back to Saas or invest in maintaining everything internally I’ve seen this movie before
7
260
I used to be a language lawyer. In the late 80s I _studied_ the ARM (Annotated Reference Manual for C++). I knew the language cold, inside and out. I could make it do backflips. I shipped a lot of code using it. A LOT. I’ve attacked other languages with a similar intensity and depth. Until recently, that was simply the only way to become adept at building software systems. I now consider the deep understanding of a language to be a supreme waste of time and effort. I don’t want to learn Rust, or Golang, or Typescript, or any of the thousands of other languages out there. I’ll leave that to my agents. What I need now is to understand the high level gestalt of the system. I want to see the systems and subsystems. I don’t need to inspect the cogs. If I truly need to understand a detail at the cog level, I’ll interrogate my agents. I’m not going to pretend to be a language expert anymore.
261
620
185
6,413
495,903
We will all be learning in coming weeks & months, that most human-made software: ▫️ Was really slow ▫️ Had many security vulnerabilities ▫️ Was under-specified and incorrect AI will rewrite it all. Many times. It will make it fast, cost-efficient, and secure. It will think about failure modes we couldn't wrap our heads around. It will prove, formally verify, load test, harden. It will turn memory-unsafe foundations into robust, optimized ones. If you ask, it'll thoroughly document it, teach you about it, make diagrams, animations, and slide decks. In many ways, we are witnessing the true birth of software engineering.
547
745
263
7,690
353,182
John retweeted
btw if you can build a category leader open source project in ai engineering right now the market acquihire rate is ~$10-$100m per ai engineer. you do not need to figure out a business model, you do not need GTM, you do not need funding. just build things clankers want.
159
125
36
3,911
410,929