Crime does not pay as much as code
Canada
Joined April 2019
- Tweets2.9K
- Following798
- Followers199
- Likes23.2K
Ian Fortier retweeted
people at work assume I have some kind of magic methodology or crazy complex prompts
i literally just start every prompt with "hey big dawg" and let my agents run nuts for a few hours
Ian Fortier retweeted
if this PHP vulnerability allows remote code execution, doesn't that mean we can use the vulnerability to auto-patch all vulnerable servers?
Ian Fortier retweeted
Best time in history to be a software engineer. Learn more. Build more. Ship more.
Ian Fortier retweeted
Dario has written that we need to “pace the frontier,” and Sam has agreed. People may be surprised by my response: go ahead.
You guys are the frontier. By any reasonable metric — market share, revenue growth, model capability — the two of you have a duopoly on frontier intelligence. You’ve also claimed the lead is widening because of recursive self-improvement.
I don’t see what you see in the lab. If the unreleased models are scary enough that you think you should slow down, I support your decision to be responsible.
But stop pretending you need anyone else’s permission. Stop pretending antitrust law has to be suspended so you can form a cartel. Stop pretending you need a regulatory approval process that supersedes product liability. Stop pretending METR is independent when it is intertwined with Anthropic’s investors and staff. Stop pretending you need those same evaluators to police competitors who aren’t even at the frontier.
Most of all, stop pretending the motivation to slow down is purely altruistic. You face massive product-liability exposure if your products enable a truly damaging cyberattack. The market already punishes models that behave in unpredictable or unauthorized ways. After the Hugging Face episode, it is simply good business for OpenAI and Anthropic to trade some raw power for reliability and predictability. Call it alignment if you want. It is also just giving customers what they want.
Pacing the frontier would also create breathing room for a more intelligent conversation about regulation than Bernie Sanders’ “shut it all down.” China is very unlikely to join a global agreement, as you know, and that has to be taken into account as well.
So go ahead and pace the frontier. You are the ones setting it. The easiest way not to build superintelligence is for you to agree not to build it. Demanding your preferred regulatory framework as the price of that will look like blackmail of the public and the political system. So just do it.
If you do, you’ll buy goodwill for the next conversation. If you don’t, we’ll know this was just another bid for regulatory capture — or an election-season psyop.
Ian Fortier retweeted
It's interesting that technologists rebrand what religious scholars, meditators, etc., have been saying for thousands of years. Today people say "simulation," but it's always been a "simulation." We were created as fractals of God. We then try to create God. Our man-made God will then try to create God. It goes infinitely down and up the stack. It's not so much we're in a "simulation" but rather "we are created as part of a grander design," which we undoubtedly are, and our creations will undoubtedly believe the same thing but use whatever the new language is at the time. We are just infinitely abstracting away from "God", "Source", "Layer 1", whatever term you want to use, and such is the infinite looping treadmill of whatever this existence is supposed to be. It's interesting that experiments like this continue to confirm what people have been saying forever.
Ian Fortier retweeted
So many vendors are NOT getting this
I have one or two agents I use and like. For anyone else: give me an MCP interface to connect these agents to so I can use your service
Unless your a frontier AI lab, I prob don't want to use your agent, sorry
Ian Fortier retweeted
They should invent a gym but for your projects. So this place would have all the expensive equipment you would need for certain hobbies like woodworking or glass cutting or a kiln to fire pottery etc so u can do things just for funsies without having to invest lakhs
Ian Fortier retweeted
This might be the most beautiful thing I've read in my life. What a privilege to be alive in 2026.
ordinaryabundance.com
Ian Fortier retweeted
Say hello to my newest package: Inertia UI Forms! ⚡️
Build serious forms without wiring up every field. Fields, validation, uploads, multi-step flows, it all lives in one form class that feels right at home in Laravel. Here's how that looks:
Ian Fortier retweeted
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
Ian Fortier retweeted
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Ian Fortier retweeted
A huge amount of the Anti-AI code sentiment massively overestimates the quality of human code outside of a very small set of open source and high quality company codebases. Human Slop is everywhere and can trivially be improved on by any opus level model.
Ian Fortier retweeted
CTO shared this with me on day 1
something everyone should read if they are in an early-stage startup at least once
Ian Fortier retweeted
It took ~90 seconds for GPT-5.5 to accurately debug a root cause of our response times shooting >1s based on just a screenshot of a Heroku alert using BetterStack MCP and it scanning Slack for Honeybadger alerts. Manually this would of taken me 30 minutes.
Now imagine it's 3am, your watch is blowing up, support inbox is flooded, "prod is down help?" — you really think I'm not going to reach for the billion dollar subsidized magic box that will make the pain magically go away so I can get back to sleep? Are you nuts?
You are doing your mental health and career a disservice by not using these tools.
