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

Building https://nitter.cf/t.co/78ySskQkMy, https://nitter.cf/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)Photo by John (@johnblythe)
John retweeted
Introducing local OpenAI & Anthropic APIs in emulate Test AI apps locally with scripted, deterministic replies ➔ OpenAI Responses, Chat & Anthropic Messages ➔ Swap one baseURL, keep your real SDK ➔ Tool loops, structured output & reasoning ➔ Inject 429s, stream timing, stalls & cuts ➔ Seeded variants repeat the same order every run ➔ No API keys, no network, zero token spend npx emulate --service ai
19
20
15
307
54,765
John retweeted
show this video to anybody that is an old school programmer that hates AI this is one of the best videos I’ve seen all month.
1,137
6,542
1,352
47,445
4,353,803
the creativity behind this website is fu*king unreal human-md.ai
548
846
311
10,377
4,855,855
John retweeted
fire from @badlogicgames - > I know too many people that kid themselves, that if the agent has written a metric ton of either linting rules or unit tests or end to end tests, the system is good > the system is not > the reason for that is they are still goal-seeking, reward-hacking little bastards and they will just lie to you...or they will measure the wrong thing > ...unless you have a very good insight into what is happening under the hood, you have *no idea* if your verifications are actually worth *anything* great chat w/ @mattpocockuk @mitsuhiko - thanks as always for the vibes youtube.com/live/ZBTegd8DUZM…
42
38
6
423
35,967
So Diogo Almeida is one of the most fascinating CEOs I have ever interviewed. born in the Philippines 2008: wins bronze for the Philippines at the International Mathematical Olympiad 2013: starts his career as a software engineer at Amazon 2017: joins Google Brain, working on cutting-edge deep learning research 2018: leaves Google Brain and takes roughly 18 months off to figure out what makes him happy travels the world, experiments with improv, art and meditation becomes a top-30 League of Legends player discovers that none of it makes him particularly happy 2020: joins OpenAI when it's still a relatively obscure research laboratory helps develop reinforcement learning from human feedback (RLHF), the technique that transforms how people interact with AI 2022: co-authors the landmark InstructGPT paper the work becomes foundational to ChatGPT November 2022: ChatGPT launches and becomes one of the fastest-growing consumer products in history 2023: contributes to GPT-4, one of the most important model releases in AI history but starts questioning the fundamental assumptions behind the technology he helped build 2024: leaves OpenAI while ChatGPT is exploding in popularity people think he's crazy for walking away co-founds TypeSafe AI with Erik Gafni and Sasha Sheng spends two years in stealth developing an entirely new class of AI models September 15, 2026: launches Jev, TypeSafe's first System One model Company makes $100M in revenue in the first 7 days of launch raises a reported $40M seed round led by DCVC October 2026: a reported $870M Series A at a $7.5B valuation, backed by a16z argues that the next breakthrough in AI will come from making intelligence cheap, reliable and autonomous My notes from my discussion with @CompleteSkeptic below: 1. Why Jevons' Paradox Does Not Cut It. We Are Going to 10x That Diogo expects a "mega Jevons paradox", with usage that dwarfs the token consumption of LLMs and AI running in the background everywhere. He expects people to stop seeing AI as something that "slops crap at them" and start seeing it as something that makes life better. 2. Why SaaS Incumbents Are Better Positioned Than OpenAI and Anthropic in Many Application Spaces SaaS companies know their customers' workflows and have the scale to fund the upfront engineering that real automation requires. Diogo argues their edge comes from being closest to the problems, not from distribution. Teams inside products like TurboTax know where to improve the interface, while OpenAI and Anthropic are "still living in their ivory tower." 3. Why We Do Not Hire From OpenAI Diogo sees getting into OpenAI as an anti-signal and says its researchers love algorithms and scaling but hate data. Data is a low-status topic at most labs, and the few people focused on the right task would want to pursue their own. That leaves researchers obsessed with algorithms, which he likens to throwing money in the furnace. 4. How the AI Bubble Could Burst and Where the Demand Shock Could Be Part of today's AI demand is driven by FOMO, from people believing they are getting good results. Diogo finds many buyers miscalibrated and overestimating what AI can do. Once they face the realities of its capabilities, demand could fall quickly. 5. What Metric Did ChatGPT Optimize for in the Early Days? Before Claude Code, ChatGPT was optimized for monthly active users rather than the best chatbot experience, which is how sycophancy emerged. Companies are now optimizing for the MAU equivalent in coding agents. Without a dedicated model, Diogo doubts they will produce a comparable one soon. 6. Why the Talent Market Is Not Crazy for Us and We Don't Pay for Mercenaries TypeSafe pays people good amounts but not the highest, which filters out hired guns. Diogo says Anthropic is suffering from mercenaries because it pays more than anyone else, and an entire market now exists to prepare candidates for Anthropic culture interviews. 7. We Wanted Sonya Huang More Than We Wanted Sequoia Diogo did not want Sequoia's money and brought the firm in because of Sonya. He values her particular shape of brilliance, which offers a perspective no other advisor gives him. One TypeSafe value is to make great decisions slowly, and he sees her as a valuable thought partner for that. (links in comments)
23
21
13
278
220,638
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
3
1
34
4,237
.@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.
130
123
28
2,860
177,451
👏 👏
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
58
looks like bumping to the claude ultra plan is becoming a holiday tradition for me. tis the season to cook. 🚀
1
37
John retweeted
Obsessing over your skill stack is the new microservices
22
23
4
279
22,383
Agree! Except @LaunchDarkly ftw
This is how agents will ship all code. → Agent writes feature-gated code → Verification gates on push (proof checking, security audits) → Agent monitors metrics You can live the future today with Vercel CLI: 𝚟𝚎𝚛𝚌𝚎𝚕 𝚏𝚕𝚊𝚐𝚜, 𝚟𝚎𝚛𝚌𝚎𝚕 𝚖𝚎𝚝𝚛𝚒𝚌𝚜, 𝚟𝚎𝚛𝚌𝚎𝚕 𝚍𝚎𝚙𝚕𝚘𝚢.
31
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:
309
619
224
8,579
818,619
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.
35
24
5
284
32,477
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.
54
51
10
1,342
70,736
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.
31
"The more secrets you have, the less happy you’re going to be." @naval
21
88
7
1,235
78,899
PSA: creating wonderful products still requires extraordinary amounts of human focus, effort, motivation, and love. And an attention span.
342
512
107
4,553
150,840
opus 5.5 is markedly dumb today. thanks fable 🙄
1
2
122
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
1,066
924,994
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
40