Austin (@Austio36) profile picture

AI Maker, Husband, Father of Twins, Dog Lover, Old Timey Blues Guitar Player, Senior Engineer Director at Doximity, opinions are my own

Joined May 2012
Photo by Austin (@Austio36)Photo by Austin (@Austio36)Photo by Austin (@Austio36)Photo by Austin (@Austio36)Photo by Austin (@Austio36)Photo by Austin (@Austio36)Photo by Austin (@Austio36)Photo by Austin (@Austio36)
33
239
7
2,409
288,411
Anthropic released code-modernization v1.0.0, a Claude Code plugin for modernizing legacy codebases Save this post if you have a legacy project worth modernizing What I find interesting is that it doesn’t just rewrite code. It tries to prove the new implementation behaves like the original Here’s how: - Analyzes the legacy system and extracts business rules - Generates a modernization plan for your approval - Rewrites or upgrades the code, even across languages - Runs the old and new implementations with identical inputs and compares outputs - Generates additional edge cases to test behavior - Introduces deliberate bugs to verify tests actually catch them - Produces a verification report with PROVEN, PARTLY PROVEN, or NOT PROVEN results It also keeps the original code untouched and requires human approval at critical steps I think this is the right direction for AI-assisted modernization, generating new code is one thing Proving that you haven’t broken existing behavior is a completely different challenge Install:
/plugin install code-modernization@claude-plugins-official Repo:
github.com/anthropics/claude…
71
183
31
2,338
189,011
Apple says you need a Mac to build iPhone apps. Today I built one on Omarchy Linux, submitted it to the App Store, installed it on my iPhone over USB, and stopped it at a breakpoint in the debugger. No Mac anywhere. It's all open source: github.com/joshuaswarren/oma…
332
870
155
9,551
542,221
I've decided to finally release my vulnerability hunting methodology that I've been using for several months now, both in testing as well as live engagements with great success. I was inspired by (and huge congrats to) the @Blackfrost_AI team open-sourcing Cyber-Frost Harness, their reproducible security-agent runtime with procedural skills, an evidence ledger, and isolated Docker targets for red/blue/purple work. 🎉 If you like the Cyber Frost Harness, and want some out of the box vulnerabilty hunting and POC development kit to go along with it - check out my VulnHunter. It's already loadable: their harness reads standard SKILL.md skills. Point skill_dir at VulnHunter's (or run its installer), and the hunting, falsification, and PoC disciplines load immediately. Repo: github.com/nealbridges/VulnH… CREDITS: This is fork of @CapitalOne original repo. I simply took it a step further on POC development and model agnostic. I'm also actively developing in my forked repo as I make more changes to it and welcome the contributions from the community as well. I think I'm doing the whole "respect who you give credit to" drama, and I asked my model to double and triple check it. So i can blame the model if its wrong. Otherwise, dont put me on blast on X if i suck at credits. /s Looking forward to developing on this further with the community.
31
220
9
1,561
105,161
Austin retweeted
Claude Ultracode is super intelligence.
275
404
158
5,208
727,932
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
1,711
6,768
1,582
56,860
8,234,620
"Let’s plan the roadmap for next quarter” is the modern day equivalent of “let’s fax everyone the strategy.” We're going into q4 planning and it makes my brain hurt. Roadmaps existed because software was expensive to build. You needed a bunch of people. Meetings. Someone moving little boxes around Jira for three months from now. It makes no sense and I'm trying to work out what we call the replacement. Maybe just "Continuous Compilation", ideas just compile to working product. I want a list of ideas that we want to continuously compile. That's the roadmap now. The cheapest way to figure out whether something is a good idea is often to just build the fucking thing. Here’s how I work now. I've done this weekly over the last few months and it works. My current napkin math is that I can usually build 6 months of old-school roadmap in a week. Sometimes more. I've also hit a wall sometimes. It happens. When we have an idea, I usually 10x the ambition and then write a prompt, not more than a page long, that basically says: - here’s the ambitious goal - here are a few use cases - here’s roughly how I think we should build it in terms of where it fits into code base, design considerations, etc.. - here’s how we’ll know if it actually works - now go fucking surprise me Agents build all night. Not even with a crazy factory or complex agent or agents. The base models are just too good for that now. In the morning I look at it. Ok, they usually build in a few hours. Usually some of it is great. Some of it is stupid. Some of it exposes that my original idea was wrong. And almost every time it gives me 5 new ideas I couldn’t have planned upfront. So we throw shit out. Who cares? We learned something. Then we change direction and send them off again. It usually takes 3 rounds before the shape appears and we've learned about the gremlins and possibilities. 95% of the time I end up building something with 10x the scope of what somebody had carefully spread across the next quarter in Jira. “What should we put on the roadmap for next quarter?” My brain now translates that to: “Oh, you're stuck in the 1500s”
33
19
8
345
40,744
Austin retweeted
🚨 IMPORTANT ANNOUNCEMENT TO THE RUBY COMMUNITY 🚨 _WHY'S SHOES LIVES BUILD A RUST-GRADE DESKTOP APP IN RUBY TODAY RUBY THINKS. RUST DRAWS. cc @cooperx86 for any media enquiries 1/6
6
15
90
6,461
🔒 HotCell moves risky Active Storage processing out of the Rails application and into isolated containers with no network or credentials, limiting the damage from vulnerabilities in tools such as libvips, ImageMagick, and ffmpeg. #Rails github.com/basecamp/hotcell
1
17
4
122
12,191
Replying to @dhh
Campfire compiled with Roundhouse + Spinel runs 5.4 times faster in rps, and consumes 1/12 of memory. No modification needed.
25
82
16
724
55,172
Hey @railsworld! As usual I've got FOMO, and as usual I'm releasing something into the #ruby wild! Introducing: ruby-laya github.com/codenamev/ruby-la… It's a #Ruby port of the open-weight System 1 decision engine Laya. Now you can get all your agent questions answered at blazing speed (33ms!) on your CPU at zero cost 🎉
5
6
3
51
5,541
“People are working 12 to 13 hours a day just to press enter.” We are turning an entire generation of technical experts around the world into the equivalent of retirees pushing a button in front of casino slot machines. Essentially the brain rot of doom scrolling social media is coming for your development team… This will have lots of long run implications on companies. Most important of which, is that it will make existing moats even more brittle. The value of automated software is not making the software faster. It is understanding your intention and making the software BETTER. Better edge. Better design. Better alpha. But if you don’t slow down and map out your intention, you will just make your shitty code faster. We built 8090’s Software Factory to do this: when execution is a costless commodity, what really matters? Over time, companies will realize that it’s: 1. Intention 2. Governance 3. Verification 4. Evidence This is what will separate orgs consuming tokens and companies encoding their edge. This generally requires top down leadership from the CEO to the CFO/CIO. Bottoms up tool adoption only increases costs and accelerates slot machine behaviors. Good luck to all the players.
I am done with this shit. It is over. The state of engineering right now is horrible. It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Humans in corporate are doing nothing on their own. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. There is no sense of victory. Nobody is resolving bugs. In reality, nobody is thinking anymore. Everything is done by LLMs. It is so soul-sucking. I would not mind it, to be honest, if we were at least given the time to check out the code and see what is going where. But no, the goal is to just ship. No matter what happens.
278
297
65
4,303
1,158,524
Let's go! 🌵
It’s time to hit the road to #RailsWorld. 2 days. 2 tracks. 1,000+ developers. Keynotes, networking, lighting talks. Tacos, BBQ, live music. ...and one mechanical bull. 🤠 Austin, here we come. See you next week! rubyonrails.org/world/2026/
2
1
38
4,401
Austin retweeted
Yep. Except: 1. This was about important internal tools. The team was stuck in some architecture nightmare of their own doing (writing it in rails but headless, with graphql api, and a SPA react app, constantly needing frontend engineers for changes). I call this kind of thing 'cosplaying an enterprise production app'. All that complexity was in the way and using straight rails was perfect in that case. 2. I make calls like this all the time. Usually someone on the team asks me to. They see what needs to happen but don’t want to be the bad guy. I’m happy to just make the call if I agree with the premise. Saves enormous amounts of meetings and change management etc. Sometimes this is jokingly referred to as Founder-mode-as-a-service here. 3. For ten years I’ve also run an internal podcast called Context, where I revisit decisions like these and explain the reasoning so everyone can learn from them. This is helpful to give people all the variables that were considered and why this was the choice made given the information available at the time. I want to teach how to make such decisions effectively without needing me. Sunk cost fallacy is a problem. 4. Any notions that Shopify is succcessful despite of me doing this, instead of because of it, will have a hard time making their argument come together I think 😄 the part of 'two weeks later tobi learns about...' is nonsese and the pivot of that project up there happens one of the more successful examples of interventions. But getting the company to work effectively with great architecture and low technical debt baggage into the right direction is literally the job, so guilty as charged I suppose. But there are always cope stories floating around like this because they are more fun, than saying 'somehow we needed tobi to stop doing silly architecture astronautics'. I can totally see that.
just leaving this here
307
230
170
6,427
1,136,228
If you're using Herdr, don't forget to install integrations for different agents you use.
8
19
4
365
61,611
Austin retweeted
SpaceXAI engineer (ex-Cursor): "right now I'm running 10-20 GrokBot agents that automate 90% of my routine i have a Chief of Staff agent. He knows about all my other bots and manages everything" in a 50-minutes podcast, a SpaceXAI engineer showed how to build a team of agents that will work for you 24/7 worth more than a $500 course on agentic engineering watch today, then read how to build a Grok agents team from scratch in the article below
264
1,360
158
16,497
5,201,299
Giving an AI agent your passwords is insane. Someone built the open-source alternative. The problem sits under every agent demo you've seen. An agent that reads your email, updates your Notion, and files your invoices needs your logins, and that handover of raw passwords and API keys is where most people close the tab. OpenConnector puts an open-source gateway between the agent and your apps. Credentials stay locked behind the runtime while the agent gets a catalog of ready-made actions for over 800 services, from Gmail and Slack to Notion and Airtable. The agent asks for an action, the gateway runs it against the real service, and the secrets never touch the model's context. The controls are the part I like. You decide which actions an agent can touch through allow and block policies, scope access per connection, hand out runtime tokens instead of real keys, and read redacted logs of every run. It speaks MCP out of the box, ships thousands of prebuilt actions in TypeScript, and self-hosts with one Docker command or a push to Cloudflare. The project is young, and the whole stack, from the provider catalog to the action executors, sits open for anyone to inspect. Agents are getting hands. A gateway like this decides what those hands are allowed to hold, and I'd rather that layer be open source than a black box.
28
127
8
986
59,270
Austin retweeted
You can literally run Opus 4.6 Max-level intelligence on a MacBook Pro. Locally.
We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With just 27B parameters, it outperforms Qwen3.7-Plus overall and shines in real-world coding & office workflows. - 262K native context, easily extendable to 1M tokens via YaRN. - Built for builders. Highly efficient, high-quality, and licensed under Apache 2.0. 🚀 The open weights for Qwen3.8-2.4T-A95B (Max-level) have also been released recently. Whether you're shipping lightweight applications with Qwen3.8-27B locally or building agents with Qwen3.8-2.4T-A95B, they're yours now! Download, deploy, and build something we haven't imagined yet. 👀👇 - Hugging Face: huggingface.co/collections/Q… - ModelScope: modelscope.cn/collections/Qw…
143
182
39
3,446
579,156
Austin retweeted
Agents on Rails: We ran 8 models against 21 atomic tasks to see which were best at writing Rails code. 3 runs each: a bug report, a security finding, a feature request. The first benchmark report with findings is now live. So: what did we discover? As of August 2026: - Most accurate: @claudeai Opus 5 by @AnthropicAI (by a hair). Solved 92% of runs (58 of 63). (But for a little more than half the cost, you get almost the same accuracy with @Kimi_Moonshot.) - Cheapest: @OpenAI GPT-5.6 Luna. 73% of runs solved at default medium reasoning effort, and all 63 of its runs cost 90 cents combined. - Fastest: Luna again, at a median of 3.3 minutes per run task. - Best combination of all three: @OpenAI GPT-5.6 Sol. 84% accuracy, costing $0.52 and 5 minutes per run. Read all the findings in the first full benchmark report from @evilmartians here: rubyonrails.org/2026/8/13/ag…
37
116
32
618
158,612
"We've started to migrate off Airtable, knowing that Bending Spoons will jack up pricing very soon" - from an engineering lead I talked to. And THIS below is exactly why: Bending Spoons bought Harvest and is 10x'ing pricing. It's their known playbook for most acquisitions
This is actually criminal. I’ve used @harvest for my freelance business for 13 years and now my Solo plan ($211/yr) is about to auto-renew as an Enterprise plan ($2547/yr).
48
30
4
772
139,258