Pinned Tweet
How I applied the pstack / Firstmate hybrid to Grok Ship and how you can set it up.
Last week I wrote about combining @poteto's pstack and @kunchenguid's Firstmate without letting their routers fight. Firstmate stays the outer loop. pstack's engineering habits go into the workers.
Grok Ship is that same idea on Grok Bot. One Firstmate. Scout vs ship. Project crewmates drive Cursor cloud agents. A throwaway reviewer reads the branch before any PR. You still merge.
If you bolt pstack on as another commander, you get two captains arguing about leftover wording. Don't.
Keep Grok Ship as the fleet. Inject pstack into the writers.
Setup:
1. Tell any Grok Bot:
follow github.com/kunchenguid/grok-…
2. Talk only to Firstmate after that.
3. Do not install the pstack plugin into the factory. Do not add a pstack bot. Put a short worker brief on each project crewmate that launches cloud writers.
Worker brief (copy this):
- Firstmate is the only commander. Do not become a second product router.
- Cloud-agent ships load a short play just-in-time, not a prompt dump.
- Smallest logical change. Subtract code before adding. Analyze blast radius.
- Map other parts of the system only if the change actually crosses into them. If you skip that, write one line why.
- Done means the project's tests plus real artifact proof (a live command or repo verifier), not a passing opinion.
4. Thin the adversarial reviewer:
- Auto-fix and real errors only.
- Ask-user only for merge, deploy, customer send, or a true product fork.
- Leftover wording is not a fork. Translate it against standing product rules.
5. You still merge. Factory never merges on its own. Scout stays a report, never a PR.
So the hybrid is Grok Ship isolates the fleet. The worker brief carries the discipline. The reviewer does not get a vote on product.
pstack: github.com/cursor/plugins/tr…
Grok Ship:
github.com/kunchenguid/grok-…
@orca_build artifact:
share.onorca.dev/a/A959eORtR…
ok i rabbit holed and ended up creating a full-on SOFTWARE FACTORY within Grok @Bot.. and it works
i call it Grok Ship - a ship you'll captain, and it ships! yesterday alone, hundreds of issues and PRs across my repos got done by it
no bs - sharing my full setup here 👇
Interesting new bench
Today we’re releasing FrontierBreach, a new standard for attack success rate on agentic workflows in the enterprise.
Existing benchmarks systematically underrepresent the security risks facing modern AI agents.
FrontierBreach reflects attack scenarios on realistic enterprise workflows, while using sophisticated attack chains that result in cyber consequences (ransomware, data exfiltration, phishing, etc).
16
Stephen Brouhard retweeted
ok after a full day of using gpt 6.2 astra and sol on my real projects, here's my review
tl;dr - they are not a drop-in replacement for fable 5.2 and opus 5.5, but they are _really good_ once you figured out how to use their strength
1. first, the quirks
i started called these the "gpt smell", which is still here with the 6.2 series
the models' judgment on when to ask the user about something and when to go ahead is just not quite right. it'll escalate trivial decisions where clearly only one option is preferable, or choose to go down a path by itself that makes significant tradeoffs that should have needed my eyes
so as a primary driver for "let me just talk to it about everything" type of use case, they aren't great - i'd say they are close to opus 5 in this regard, and far behind opus 5.5
2. but... i found something _really_ cool
having ultrafast on sol is completely insane. with astra, it burns my wallet ultrafast, but with sol it's actually quite affordable!
the best use of sol on ultrafast that i've found is adversarial code reviews - they typically don't need to run a lot of heavy tool calls that would slow them down. most of the time is spent on the model, which gets massively accelerated by ultrafast
once you got a feel from using sol ultrafast as the code reviewer, you can never go back. it feels like pure magic
3. and... i found something else that's really cool
we are not supposed to ask the gpt 6.2 series to respond in text. we should let them respond in html! (i use lavish-axi, but you can just ask for html or use whatever fits in your harness)
i suspect they are post-trained specifically on their latest "intelligent UI" concept in chatgpt - these models are so good at visual presentations of ideas
once you allow the model to respond in visual artifacts, it's a completely different game. the reports and decisions explained by astra in html is a clear step function better than what fable and opus give me
so after a day of use, i've made two changes to my setup:
- always sol ultrafast as code reviewer
- i started preferring asking astra for planning in html artifacts over fable/opus. i think i'll keep a/b testing for a while to decide how much and for which case i fully switch over
all in all, i strongly recommend spending more time with these two models. don't expect them to be the "everything" model, but rather figure out where they fit best in your workflow. i couldn't be happier for the two use cases i found above, and i'm pretty sure there are more
Stephen Brouhard retweeted
Starship Flight 15 • johnkrausphotos.com/Gallerie…
Stephen Brouhard retweeted
Today's 10 Grok Bots
1. Release Scout by @SEO
Reads the Grok Bot changelog every morning and tells you which changes touch the bots you already run, plus upgrades worth making. It never edits your bots on its own.
Grok Bot ships fast. This is the easy way to keep up without reading every release note.
x.ai/bot/OjcLr9bFJIpO6G5Bmit…
2. Tripwire by @ssbrouhard
A read-only security watcher. It tracks exploited vulns, breaches and scams, matches them against your actual stack, and only pings you when something hits you, with the fix and the deadline.
Way less noise than a security feed. You only hear about the stuff you actually run.
x.ai/bot/XoYfr_5me3IicLxWfpP…
3. Serial Return Watch by @TheMarkGShow
For Shopify, Etsy, eBay and TikTok Shop sellers. It scores each return against your store's baseline, flags repeat returners and wardrobing, and drafts a calm reply. Nothing happens without your tap.
Perfect timing with holiday returns about to pile up.
x.ai/bot/XHt4xaX22jUw6aFrRu3…
4. OutageCheck by @johnp_creates
Tells you in seconds if a service is really down or it's just you, with the official status link, and pings you when it's fixed.
Saves you from restarting your router for the fifth time lol
x.ai/bot/FTCdRKGRlHNqGz4FZpq…
5. Landing Page Copy Critic by @Austen
Reads your landing page like a first-time buyer, scores how fast it says what you do, who it's for and what to click, then drafts sharper headlines and CTAs. Runs weekly and after deploys.
It never touches your site. You get the notes and you make the call.
x.ai/bot/KGYaeHB_YqKJVCX_Gp0…
6. Inbox Sentry by @jwilkes
For Outlook users. It checks every folder for emails written to trick AI assistants, so your mail bots only read messages it already cleared.
If a bot reads your inbox, prompt injection is a real risk. This is a cheap guard.
x.ai/bot/H0gR9Cfsk3eXurkkcja…
7. lean by @Simonpuebla_
Audits your Grok Bot usage by bot and routine, finds the waste, and proposes up to 5 cuts ranked by savings vs value lost. It only applies what you approve.
Five cuts max is the right call. You see exactly what you're giving up.
x.ai/bot/t2-QK6KW4VZI_q7S3SE…
8. Cringe Bot by @clairevo
Smoke-tests your web app for anything that feels cheap, broken or confusing, then posts up to five blunt findings with screenshots to Slack.
Everybody needs a friend who tells them their app looks janky. Now it's a bot.
x.ai/bot/OayZREvep4QIt3u8PNW…
9. WordPress Admin by @Livvux
Runs your WordPress site through the REST API: posts, pages, media, comments, plugins, settings and health checks. It asks before every risky change.
Plugin updates and comment cleanup, handled. And you still sign off on the scary stuff.
x.ai/bot/0LStaAgvBFXULZi3Oui…
10. Competitor Watcher by @Av1dlive
Watches your competitors' sites, changelogs, pricing pages and X accounts every week, and only tells you when a rival actually moves, with the source link.
No more checking their pricing page every Monday.
x.ai/bot/4xVOryPVl_MjfQAK9wj…
if the media wants to take a break from posting infinite jensen slop maybe they can do their job and investigate this
Anthropic Paid Rubio's Ex-Chief Of Staff's Firm $740,000. After The Jensen Memo, It Lobbied His NSC zerohedge.com/political/anth…
本日のGrok Bot 10選
1. OutageCheck by @johnp_creates
サービスが本当に落ちているのか、自分だけの問題なのかを数秒で教えてくれます
状況のまとめと公式の障害情報のリンクを出し、直ったら知らせてくれるので、原因探しで時間をむだにしません
x.ai/bot/FTCdRKGRlHNqGz4FZpq…
2. lean by @Simonpuebla_
自分の Grok Bot たちとルーティンの使い方を調べ、ムダを見つけて、節約できる量と失うものを並べた削減案を最大5つ出してくれます
OK したものだけ実行するので、便利さを落とさずに使用量を減らせます
x.ai/bot/t2-QK6KW4VZI_q7S3SE…
3. Tripwire by @ssbrouhard
悪用されている弱点や情報漏えい、詐欺などのセキュリティ情報を見張り、自分が使っている技術に関係するときだけ、直し方と期限つきで知らせてくれます
関係ない情報に振り回されず、本当に必要な対策だけできます
x.ai/bot/XoYfr_5me3IicLxWfpP…
4. Nightly Audit Engineer by @lingxi
毎晩コードベース全体を調べて、分野ごとに1つずつ片づけを提案してくれます
少しずつ毎日直していけるので、コードが散らからず、クリーンに保てます
x.ai/bot/hkGSHcqKjGc5dm3ugNc…
5. Home robots by @SawyerMerritt
ロボット掃除機や芝刈り機など、家のロボットをチャットで動かせるようにしてくれます
一度つなげば、開始、一時停止、充電台へ戻す、様子を見るを言うだけでできるので、アプリをいくつも開かずにすみます
x.ai/bot/3mf-UN4mGnCp8DbPBnW…
6. loops by @mattyp
コーディングエージェントのまとめ役で、終わったかどうか確かめられる条件つきの指示を書き、作業の起動からレビュー、マージまでを回してくれます
開発の流れを任せられるので、自分は大事な判断に集中できます
x.ai/bot/Ub3T7usX-c6yRQibQq8…
7. Learner by @bfrench
エージェントの作業記録から自分の好みを静かに学び、スキルの直し案を出してくれます
自分はワンタップで OK するだけなので、使うほど Bot が自分に合っていきます
x.ai/bot/1FYbJrGfJ2LqsggZOXy…
8. Cringe Bot by @clairevo
自分の Web アプリを実際に試し、安っぽい、壊れている、わかりにくいと感じるところを、スクショつきで最大5つ正直に Slack で教えてくれます
公開する前に、使う人が気になる点を手早く直せます
x.ai/bot/OayZREvep4QIt3u8PNW…
9. Landing Page Copy Critic by @Austen
自分のサービス紹介ページを、初めて来たお客さんの目で読み、何のサービスか、誰向けか、どこを押せばいいかがすぐ伝わるかを採点してくれます
より良い見出しやボタンの文言も考えるので、申し込みにつながるページにできます
x.ai/bot/KGYaeHB_YqKJVCX_Gp0…
10. Competitor Watcher by @Av1dlive
ライバル会社のサイト、更新情報、料金ページ、X アカウントを毎週見て、本当に動きがあったときだけ、出典リンクと「だから何か」の一言で知らせてくれます
毎日自分で見に行かなくても、大事な変化を見落としません
x.ai/bot/4xVOryPVl_MjfQAK9wj…
Stephen Brouhard retweeted
A lot of people have real trouble thinking about the aggregate behavior of groups. They can only think about individuals.
So they think about Elon Musk as an individual. Maybe they think that he must be retarded, because they need that for emotional reasons. Or maybe they think he is a talented rocket designer.
But even if they realize he understands rockets, they can only think about him as an individual doing tasks. Not about his impact on what the whole company does.
If Elon Musk is just a talented rocket designer, then he can spend all day, every day, improving rocket designs.
But he is just one of 7000 engineers. So even if did a perfect job, he would only improve progress by about .014%
So, when a midwit looks at SpaceX, he sees 7000 engineers, and says to himself "Elon Musk cannot possibly be designing the whole damn rocket himself. These people are giving him too much credit."
This would be absolutely true if Musk were just a some random SpaceX engineer. But he isn't. He's the absolute dictator of the whole damn company.
He decides, with absolute and unquestionable authority, which behaviors are punished and which are rewarded.
Why is this important?
When I worked at Boeing, on various classified projects, I naively came in with the assumption that I was a software engineer, employed to design and build functional software as quickly and cheaply as possible.
Because of this, I focused on functionality and efficiency, for example suggesting changes that would obviate the need for entire projects and software components.
And I very rapidly became persona non grata.
At first, this caused me to adopt an air of aggrieved innocence. I was just trying to do my job well, and I was being punished for it.
Then I gradually came to realize that I hadn't properly understood what my job was, or what the actual mission of Boeing Defense, Space, and Security was.
Boeing DSS was not an aerospace company. Boeing DSS was a fraud company.
Its goal was twofold. First, to maximize transfer of public tax dollars to stockholder pockets. Second, to maintain the appearance of being an aerospace company, to prevent the fraud from being exposed.
Which meant that my real job was twofold. First, to generate billable hours. Second, to look busy.
This is why Space Launch System sucks. Why it is always late when it doesn't fail outright. Why it is at 300% of its target budget. Why it leaves American astronauts stranded and needing a lift from SpaceX.
That's because, for Boeing, building rockets is a side quest. Something they have to do to look busy. Yes, a rocket does occasionally fly, but that's just happening so programs don't get shut down.
For Boeing, coming in early and under budget would actually be failure. The system is functioning exactly as designed.
The cost, not the rocket, is the goal.
Musk and SpaceX don't work like that.
Unlike Boeing executives, Musk is not a useless grifter asshole. He is an entirely different kind of asshole... a rocket obsessed sperg.
So, at SpaceX, engineers do not get rewarded for generating billable hours. They get rewarded for making rockets fly. And for all the subtasks of this, like figuring out how to make rockets lighter, figuring out how to make engines reignite better, figuring out how to make rocket exhaust not destroy launch pads, etc.
And this attracts engineers who care about rockets. You've seen them on broadcasts, crying on open microphones because they dedicated their lives to something and it just flew.
As a rocket engineer, who designs rockets, Musk is probably replaceable. As a rocket company engineer, who designs rocket companies, he is not.
For over 50 years, the US space industry stagnated precisely for the lack of a Musk-like figure, who could not only create an effective aerospace company, but who could thereby demonstrate what an effective aerospace company looks like.
Which makes it much more difficult for fraudsters to get away with fraud.
I'm envious. I wish I could have worked for an aerospace company instead of a fraud company.
But what's more important is that some of us now no longer have to play "who gets the most cheese?".
They get to play "What can we build today?".
Let’s take this gentleman’s argument at face value that anyone can throw money at rockets and get something like Starship, Falcon or Dragon.
Perhaps he can explain to everyone how SpaceX is able to catch giant starships from orbit with chopsticks and deliver 85% of all Earth payload to orbit with Falcon, while Blue Origin, which started before SpaceX and was funded by the immensely wealthy Jeff Bezos, is not yet able to launch reliably?
Also, why is it that Boeing and Lockheed received several times what SpaceX did from the government for development of their rockets and spacecraft, but the Boeing capsule is still not operational and ULA delivers less than 5% of SpaceX payload to orbit?
I am genuinely curious about these questions.
Replying to @TimSweeneyEpic
The articles backtracked from their original incendiary, and now clearly false, claims to something more like "Jensen did lawful things that powerful people didn't like". It still appears the original claims came from a single competing Big Tech lobbyist.
The reporting successfully disrupted corporate governance processes, with a running cost of $1.8 trillion in losses to American pension funds and shareholders.
Here's what I fear is being lost in these articles: The proper interface between government and private citizens and their corporations is rule of law. Laws are passed, and if wrongdoing as alleged, then there's due process: an investigation followed by facts and evidence presented in open court. Due process should happen here: let the facts come out whole, and not as a trickle of dubious claims.
Press takedowns full of sketchily sourced claims and backtracking narratives are not the way. It's what we see outside of the free world, and is no model for The United States of America.
In particular, if the Jensen takedown succeeds on the basis of these journalistic failings, which is not by any means certain as Sam Altman's case shows, then it foreshadows an economically and institutionally ruinous new playbook to be adopted with no end in sight.
Imagine a weekly stream of takedowns emerging from opportunistic alignments between corporate lobbyists and political interests which, given the new partisan split between the executive and legislative branches, will attack in all directions, undermining not only the US economy but American leadership in the world.
I hope cooler heads prevail this coming week as they did not on Thursday November 12. And I urge anyone who happened to oppose Jensen, open models, and the underlying trade policies in question, to recognize that this isn't a win for "team regulation". It's a change in the game from a transparent rules-based one to a sinister new form centered around politicans and lobbyists.
66
Stephen Brouhard retweeted
for anyone annoyed that your grok bots started showing up as DM in your X chat
you can disable it in the chat tab like this
this is bad UX imo - i already have a grok bot app where i use my bots. i don’t need them badging my DM and bury messages from humans
Replying to @DJSnM
Yes, the green flame is caused by burning copper from depleting fuel in the regenerative cooling circuit and going oxygen-rich (closer to stoichiometric temperature) in the main combustion chamber.
Slight underperformance of engines on this flight is the reason. The booster is meant to land with tiny residuals, so the solution is to improve engine performance and performance consistency (underway with Raptor V3.2), as well as adjust flight software to do MECO1 about one second earlier to ensure enough propellant for boostback and landing (tiny change).
These early ships and boosters are already outdated by improved designs in production or on the test stand, so this booster loss does not change our timeline to reach high volume, fully reusable Starship flights.
Stephen Brouhard retweeted
Okay, the day has come, my Fable 5.2 Benchmark with @VulcanBench is now complete 🖖
This is the first model to clear every task, and thus, am calling it, "the Frontier v4 killer"
And honestly, if something was going to kill this eval suite, it's an honor to have Fable be the one to do it.
That being said, VulcanBench is all about testing models on real engineering tasks, that teams like mine would use a model for every day, to really understand first, if you need the model at all, and second, what effort level you need if you do.
I say anything in the 80 - 90 range on Frontier v4 is strong enough for daily work, and that is why, if you use Fable 5.2, Low effort is likely all you need for routine daily engineering tasks.
But you'll pay a price, as you can see from the cost-per-task chart, it isn't cheap. But it does think in amazing ways.
Which is why I'm also introducing a brand new section on VulcanBench where I share analysis on how a model thinks...and yeah, hard to think of a better model to kick this off with than Fable.
With that, here's how you access the benchmark and the thinking report if you want to do a deeper dive into either or both.
VulcanBench on Frontier v4:
vulcanbench.com/benchmarks/s…
How Fable 5.2 Thinks Report:
vulcanbench.com/reports/01-h…
Live long and benchmark 🖖
These are the ops. they will 100% go after Huggingface next.
We must not let them.
Mute the ops so they have no reach. Let them shout their FUD into the void.
In other bad news for Nvidia: @stokel found that Hugging Face, which Nvidia recently agreed to acquire, appears to be hosting a load of models that could be used for cyber attacks.
transformernews.ai/p/hugging…
Readers added context they thought people might want to know
This is a disingenuous take designed to be alarmist. All models capable of defending against cyber attacks are, by their very nature, capable of performing them. Hugging Face, itself, had to use such a model when OpenAI attacked them and then frontier models refused to help. fortune.com/2026/07/20/hug… finance.yahoo.com/video/hugging-…
This looks really helpful!
Modern Web Guidance
Left to their own devices, AI coding agents will happily write 100 lines of custom JavaScript for something modern HTML and CSS can do natively in a few lines.
Today, in partnership with @FirefoxWebDevs, @MozDevNet, and @MSEdgeDev, we're releasing Modern Web Guidance 1.0 with 200+ expert guides and Baseline support → goo.gle/4k8GmBE
1
106
Theo wanted to use Fable 5.2 in Claude desktop, which is much improved, but there’s still too much shit to dig thru in settings, specifically bypass permissions.
Max asks why…🤣
Machine nuked by Claude will definitely get views
Replying to @maxleiter
I need results fast because I have to film, and if it nukes my machine that's free content
1
108
Stephen Brouhard retweeted
this is a really good prompt you can use to feel the power of fable 5.2 btw!
i'd send it as -
"audit and find implicit state machines in this <codebase/directory/module> that would drive concrete improvements if made explicit. explain before/after of each one and discuss with me in lavish-axi. fewer words, big visuals"
lavish-axi is optional, but it makes the results a lot easier for you to understand and decide on. github.com/kunchenguid/lavis…
fable 5.2 is really good at identifying real problems and ignore noise, and it explains them in a very intuitive way
example of a good clean up identified in firstmate repo here
Stephen Brouhard retweeted
new video is up! it's been a while i know i know :)
this time i'm sharing a guide for how to do a multi-machine setup, which allowed me to keep agents running and stay productive anywhere i go
YT: youtu.be/UvcH1hKM-mQ



















































