Building Vector: The Enterprise AI Operating System @ https://xitter.cf/t.co/D38E5CXwiA, and LifeOS: The Human Fulfillment Harness @ https://xitter.cf/t.co/muV0Un09sA | Ex: Apple, Robinhood, HP
San Francisco Bay Area
Joined March 2007
- Tweets29.6K
- Following1.6K
- Followers161K
- Likes24.5K
Pinned Tweet
I feel like everyone is going to figure out at the same time (in 1-4 months or so) that our biggest problem today with AI isn’t actually an AI problem.
The problem is we’re not giving our AIs clear enough definitions of what we want.
So our AIs basically go off and build in some direction, but not exactly the direction you want to go in.
This problem has three main parts:
1. You knowing what you want
2. You being able to articulate that thing thoroughly and accurately
3. Your AI being able to do that thing
Everyone assumes the problem is with number 3, but it’s usually a combination of 1 and 2.
The next biggest advancement in AI (or one of them anyway) is going to come from harnesses building this concept of ideal state, evals, and hill-climbing directly into their DNA.
In the model providers can help as well by eliciting this from the user and building this before any work is done.
Ideal State, Evals, and hill-climbing. This is where it’s at.
I've been working for a while on a site that helps answer one question:
"How much is AI actually affecting cybersecurity outcomes?"
I've got tons of data sources and analysis in here. If you're in this space, help me improve it!
vulnerabilitydata.io/
Patch PHP today and make sure to restart your workers. Exploitation has gone from thousands of attempts to millions within hours.
securityonline.info/php2shel…
I think I have a good analogy for what's about to happen in cyber.
It's pitch dark. Always has been. And the world is dilapidated buildings and rats and maggots and other creepy-crawlies. The whole world.
And we just invented flashlights.
How bad is this Gitlab issue? About as bad as it gets.
Anyone on the internet can take over an exposed, self-hosted GitLab server without logging in, on any version from the last 12 years.
Shodan is showing ~60K exposed servers online, which is a lot, but there are are far more internally for anyone with a foothold already.
🚨 CRITICAL: GitLab flaw (CVSS 10.0) affects 12 years of releases.
CVE-2026-110264 could allow unauthenticated remote code execution on self-managed servers.
Read - thehackernews.com/2026/10/cr…
ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ 🛡️ retweeted
Effective Immediately, all organizations using PHP for their systems are advised to be prepared for an update addressing two critical vulnerabilities. PHP is widely used for web applications. These vulnerabilities often provide a direct path to the server's file system or database. If an immediate update is not feasible, it is recommend that organizations take the system offline until it can be fully mitigated. NSA will follow up shortly with more specific guidance.
The middle went first, but the validation is abut to get eaten as well by both the models and the harnesses.
In this three-tier model it’s the “knowing what to build” that will be our last hold out.
My hypothesis, after months of building with agents every day.
Software work has three parts. Deciding what to build. Building it. Checking that it works.
For decades the middle part was the expensive one, so we organized everything around it. Job titles, team sizes, estimates, how agencies charge.
Agents are collapsing the middle. The two ends aren't getting cheaper at all. If anything they matter more, because a bad decision now gets built in an afternoon.
So the valuable person is whoever owns the ends. I call that person a product builder.
💯. And as predicted.
1. Better and better open models with no controls on them
2. Tons of new harnesses designed to help people do harm across cyber, organized crime, etc.
3. Governments start making it illegal to use open models.
And guess what:
reuters.com/legal/government…
Transition from vulpocalypse to breachpocalypse is here. IR firms are saturated & turning away work. Now one hacker unleashed AI agents on 1,200+ websites, compromising 100+ for ~$5,000 in tokens. $50 per hack. Agents won and compromised targets. reuters.com/legal/government…
ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ 🛡️ retweeted
Having Fable 5.5 be a major jump on some of these would be fantastic, but the real spear in the side of OpenAI would be removing the Fable Stress.
So basically having Fable work just like Opus does now, but maybe use your limits a bit faster. But nothing dramatic. And without its own dedicated limit.
Double spears and a Thanos snap would be if they did this while raising limits somehow to reduce even more anxiety. But that's just wishful thinking.
Either way, can't wait to see it.
Fable 5.5 probably definitely tomorrow.
Rumors:
- Better at reasoning and intuition
- Infers intent rather than taking instructions literally
- More ambitious. Ask it to fix a bug and it fixes the deeper root cause
- Does creative, “out-of-the-box” thinking
- Can invent algos to predict stocks
- Bestows complete and eternal enlightenment on first response
AND I’d bet it has major efficiency gains like Opus 5.5. Icing on the cake would be usage for all subs.
Prepare yourself in mind, body and spirit.
Having Fable 5.5 be a major jump on some of these would be fantastic, but the real spear in the side of OpenAI would be removing the Fable Stress.
So basically having Fable work just like Opus does now, but maybe use your limits a bit faster. But nothing dramatic. And without its own dedicated limit.
Double spears and a Thanos snap would be if they did this while raising limits somehow to reduce even more anxiety. But that's just wishful thinking.
Either way, can't wait to see it.
Fable 5.5 probably definitely tomorrow.
Rumors:
- Better at reasoning and intuition
- Infers intent rather than taking instructions literally
- More ambitious. Ask it to fix a bug and it fixes the deeper root cause
- Does creative, “out-of-the-box” thinking
- Can invent algos to predict stocks
- Bestows complete and eternal enlightenment on first response
AND I’d bet it has major efficiency gains like Opus 5.5. Icing on the cake would be usage for all subs.
Prepare yourself in mind, body and spirit.
Definitely feels super fast to me.
Love the continuous improvements.
Cloudflare is going to start scoring bots on behavior over time, such as honoring robots.txt, etc. Love it.
blog.cloudflare.com/verified…
You sound completely awesome so don’t take this as criticism.
Most of the stuff you’re talking about here is captured much better and more differently in the models already.
You shouldn’t give it help with technical coding concepts. It wastes your context window and can make output significantly worse.
What I recommend is using your harness’s context files to describe how you like your code to look. Personal preferences. Style. Favorite languages. Etc.
Basically, what, not how.
Try it. I think you’ll be pleasantly surprised.
I created a new system of measuring work output called Deeds that addresses this issue. workdeeds.ai
But to answer your question (since I asked the same one), it's because PRs are collaborative artifacts. They're very much needed when there are tons of people in a codebase. Or at least more needed.
I created Deeds because more and more code is now going to be made by single builders.
Why are you still using pull requests?
Is it for code review?
If so, do you really think your or your colleagues catch bugs and mistakes that an Opus 5.5 or Fable or Astra won't find? You can literally spawn all three of them and have them check four times each.
(Also, don't tell me you don't have a "stamp plz" Slack channel or group chat somewhere.)
Is it for knowledge sharing?
Surely there's better ways for that now than the PR, no? We have models that can generate explainer videos, presentations, podcasts, games, quizzes, walkthroughs, ... for any piece of code it can reach.
Is CI the reason?
Well ackshually, CI means continuous integration and its original meaning is the *opposite* of having long-lived branches and PRs.
But, leaving that aside, your agents are hopefully already running the tests before they push something, and hopefully they can run as long as they want and don't block you so they can run the whole test suite and generate "irrefutable proof" and end-to-end demo videos and so on... And so they run the tests and confirm and then you push to a branch and everything runs again and then you merge and then it runs again? That doesn't make sense, does it?
Maybe you work in open source and you accept contributions, in which case I can't speak to the value of pull requests. It's been 2 years since my last OSS contribution. But from what I heard, the time of the PR is coming to an end in OSS too?
I honestly don't get why people still stick to PRs.
With agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.
Don't slow yourself down by having all the changes pile up in a PR.