Dylan B (@StarmorphAI) header
Dylan B (@StarmorphAI) profile picture

@Render DevEx Engineer

Phoenix Arizona
Joined December 2022
Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)Photo by Dylan B (@StarmorphAI)
Dylan B retweeted
We used to only care about how our products look to the human eye. Now there are completely new layers: 1. AX – how agents experience and interact with your product (WebMCP, MCP, APIs, Poppy, A2A, etc) 2. UAX – how humans perceive your product inside their agent (MCP Apps, A2UI, UI SDK, json-render, voice hints, etc) The UAX layer is fascinating and overlooked, and it's where a lot of the new innovation opportunities are.
24
31
9
321
18,337
Ready to move your coding agent workflows to the cloud? Here's an open source software factory you can self-host on @render! The repo also demonstrates how to build secure, production-ready agentic applications. Fork it, bring your own agents, and extend with custom flows!
3
2
5
95
Render has been named to the inaugural 2026 AI 100, a list of 100 private companies defining the age of AI. More developers are building agents, and they need new infrastructure: a safe place to run untrusted code and a way to reliably coordinate long-running, distributed work. That’s exactly what Render Sandboxes, Workflows, and Shared Filesystems are for, with more key AI primitives coming soon. Thanks to @EricNewcomer and @BessemerVP, and to all the developers building with us.
8
14
5
72
472,740
Dylan B retweeted
Introducing Render Sandboxes: a computer for every agent. render.com/sandboxes
25
25
14
220
4,483,323
Sundar Pichai on the earnings call: 'This rapid progress underscores our incredible model momentum. We are at the point where AI is helping us increase our training and launch velocity. I would expect the next twelve months to see continued acceleration because of RSI.'
63
118
27
1,620
174,757
extremely good explanation
Many of you don't understand how serious this is, so let me break it down. In computer science there is a famous kind of puzzle called 3-SAT. You are given a long list of yes-or-no switches and a set of rules about how they must be arranged, and you have to find a combination that satisfies every rule. The obvious way to solve it is to try every combination, but each new switch doubles the number of possibilities, so a puzzle with a few hundred switches would take longer than the age of the universe to brute force. For decades, the smartest people in the field found clever tricks that made this a little faster, but every trick still hit the same wall: the time required kept exploding as the puzzle grew. About 25 years ago, two computer scientists, Russell Impagliazzo and Ramamohan Paturi, working with Francis Zane, turned that wall into a formal idea. They proposed the Exponential Time Hypothesis, which says this explosion is not a failure of human cleverness but a law of nature. No algorithm, however brilliant, will ever solve 3-SAT without the time blowing up exponentially. Nobody could prove it, but almost everyone believed it, and it became one of the foundations of modern computer science. Researchers used it as a measuring stick. If you could show that solving some other problem quickly would also crack 3-SAT quickly, you had shown that problem was hopelessly hard too. Hundreds of papers, across scheduling, graphs, logic and much more, rest on this one assumption. Now an internal AI model at OpenAI claims to have broken it. It says it found an algorithm that solves these puzzles meaningfully faster than the hypothesis allows, and it has checked the proof in a computer verification system called Lean. And here is the remarkable part: the very people who proposed the hypothesis, Impagliazzo and Paturi, along with MIT's Ryan Williams, are now leading the public review of whether a machine has disproved their own idea. So what happens next? If the disproof holds, a large part of theoretical computer science has to be revisited. Every result that said "this problem cannot be solved faster, assuming ETH" loses its foundation, and researchers will have to work out which of those walls were real and which were simply where we stopped looking. It does not mean everything becomes easy. The new algorithm is still slow in absolute terms and this is not the famous P versus NP problem being solved. But it means our map of what is possible was wrong in a place we were very confident about, and it was an AI that redrew it. If the disproof fails, the hypothesis survives and the field breathes out, but we will still have watched an AI produce serious, checkable work on one of the deepest questions in the discipline, closely enough that the founders of the idea had to take it seriously. Either way, something has shifted.
7
13
1
492
110,444
Dylan B retweeted
Manage your Render infrastructure without leaving the terminal. Learn how to: - Trigger deployments - Manage Postgres & KV stores - SSH directly into web services - Install Render Agent Skills - Automate CI/CD pipelines with non-interactive mode Full video: youtube.com/watch?v=pILqLLFi…
1
5
23
2,489
You don’t need to be naturally talented, you need to be unnaturally persistent.
11
356
2
2,694
51,764
Dylan B retweeted
Not every seed of service you plant will sprout and flourish, but if you keep planting, eventually some of them will. That's just the math of good deeds and good faith.
67
132
8
1,997
52,037
We're launching fast, fully-managed shared filesystems for sandboxes, workflows, and every other service type on @render. Sign up to get early access! render.com/shared-filesystem…
7
10
1
72
5,412
Dylan B retweeted
OpenAI uses Render to ship apps like gpt-oss playground and ChatKit Studio, supporting hundreds of thousands of concurrent users. Recently, they used Render Workflows + Codex to launch a guide generation agent on the @OpenAIDevs site. Here’s how: render.com/customers/openai
2
15
1
32
1,687
Dylan B retweeted
spawning up a fleet of agents
7
2
146
8,699
Dylan B retweeted
Want a Render service to spin up Cursor Cloud Agents? 🤖 Learn how to deploy our new open-source template to self-host execution on Render: 🔒 Keep credentials & code safe in private, isolated workers ⚙️ Trigger agents via HTTP, Slack, or Linear 🚀 Scale seamlessly with Render Workflows Watch the full guide & deploy the blueprint: youtube.com/watch?v=iDvDkrBY…
3
4
25
2,481
Dylan B retweeted
OpenRouter now runs inside @render Workflows. Stop putting LLM batches in your web service. Each prompt becomes its own task run, queued, retried, and fanned out by Render, with the model call routed by OpenRouter.
17
11
2
113
183,279
The WebMCP Challenge is here. We’ve teamed up with @ChromiumDev, @CloudflareDev, @ShopifyDevs, @vercel, @render, and @Netlify for a 10-day hackathon. Up for grabs: $35,000 in cash prizes, Codex Micros, ChatGPT Pro subscriptions, and more prizes from our supporters.
145
302
151
3,715
1,917,633
Dylan B retweeted
New video: Infrastructure for Agentic Applications Watch here → youtube.com/watch?v=DCy6YjJJ… We break down the pros/cons of 3 agentic patterns for long-running, stateful AI agents: 1. Queues + Background Workers 2. Render Workflows 3. The Combined Architecture (best for scale) Plus a live deploy of a Code Review agent using Blueprints — Web Service + Workflow + Postgres in one go. GitHub + tutorial in the description.
1
2
11
1,737
Introducing Grok 4.6. It delivers frontier intelligence and is a significant improvement over Grok 4.5 at the same price.
1,851
3,305
2,671
30,083
26,968,061
Dylan B retweeted
Introducing Muse Glimmer, an open-weight 30B-parameter model optimized for local, always-on agent workflows. Muse Glimmer delivers strong performance on key agentic use cases and benchmarks compared with leading models in its size category, and is designed to run entirely on consumer hardware like a Mac or PCs with performant GPUs. In keeping with our long tradition of sharing fundamental AI research, we’re releasing model weights under a permissive Apache 2.0 license. 🧵👇
371
1,091
432
8,215
1,439,984
Dylan B retweeted
the bottleneck is increasingly knowing what you want
728
1,381
322
15,458
926,733