Building @CleanSlop | Meta tools for AI devs and bringing reliable engineering practices to slopcoded apps | Prev @PowerLoom @BlockVigil
Joined October 2014
- Tweets1.4K
- Following419
- Followers700
- Likes21.5K
Working with @SwaroopH is super fulfilling on this. His crazy product brain took over the harder work of exposing the @CleanSlop backend harness to multiple carefully crafted pathways of integration.
A swiss army knife agent CLI, login via Link or GitHub, MCP, local code uploads, 402 standard payments via Link. And there is more on the way.
Watch out for next week's shipping updates.
I got early access right the night before we launched @CleanSlop on Product Hunt.
"if you decompose enough, model providers can't even figure out what you're working on"
Speaking of decomposing queries, right after the launch, the first thing I did was get on to was running a complete audit on our scanner engine with Jev and finding out the leaky reasoning pathways.
xitter.cf/anomit/status/21009493…
was at a community event and was asked a somewhat sad question: should developers be afraid of the labs eating the new possibilities jev opens up?
with AI (system one) + software (system two):
1. there's no going back to a world without system one models
2. you control the software!
3. there's no way AI could beat the efficiency of this combo
4. you don't even send the model providers your whole program logic
I think the days of "wrapper" apps will be seen as some of the darkest in software because people essentially did all of their programming in a system message and sent it over to a third party who was incentivized to bake that behavior into their 1st party product...
keeping your logic in code and only asking AI for the minimum reverses that and keeps all of your logic yours. if you decompose enough, model providers can't even figure out what you're working on
The Renessaince Period's ideal: Vitruvian man. Supposed to denote the inherent perfection and divinity in a human.
The post-capitalistic gambler influencer streamer era's ideal: iced out drip.
No aspiration other than to be a petty thug.
GTFOH.
"keeping your logic in code and only asking AI for the minimum reverses that and keeps all of your logic yours."
Devs are sleeping on the fact that you can use this to audit leaky reasoning in their intelligent systems. Run Jev evals on the logic pathways where you expect specific state transitions to happen based on specific states, and if they don't match, you got a problem on your hands.
was at a community event and was asked a somewhat sad question: should developers be afraid of the labs eating the new possibilities jev opens up?
with AI (system one) + software (system two):
1. there's no going back to a world without system one models
2. you control the software!
3. there's no way AI could beat the efficiency of this combo
4. you don't even send the model providers your whole program logic
I think the days of "wrapper" apps will be seen as some of the darkest in software because people essentially did all of their programming in a system message and sent it over to a third party who was incentivized to bake that behavior into their 1st party product...
keeping your logic in code and only asking AI for the minimum reverses that and keeps all of your logic yours. if you decompose enough, model providers can't even figure out what you're working on
Anomit retweeted
Actually the chronically negative you can identify in hiring and avoid
The real damage to startups is done by 'Smart Skeptics'
Who are smart, sound even smarter than they are, are great at raising objections, can hold great intellectual conversations, have a lot of anecdotal evidence about everything.
But can't execute/move metrics/ solve hard problems even if their life depended on it, because they are skeptical about everything.
And they dissuade the believers as well.
Avoid them like a plague
3.5 weeks on Jev.
1.5 weeks on Clef.
First-hand observations
- Jev is still orders of magnitude faster and cheaper.
- Jev is not hesitant to mark "not sure" in confidence scores against evaluation questions instead of stretching out reasoning, which clef seems prone to.
Connected @CleanSlop MCP live on call with @SwaroopH in Cursor IDE.
Frictionless application of changes in-editor.
Complete agentic support dropping this week for select beta users! DM us for early access.
Anomit retweeted
Now that I'm working with customers who vibe code, it's time to put myself in their shoes and ship in public.
Next few weeks: one app a week, 1–3 prompts, one hour max. No engineering, no prompt wizardry.
Introducing #1: Quietlist, a to-do list only you can read 🔒
Link in 🧵
You can load my system with a year's worth of psychedelics from DEA busts in the Colombian jungles, but being born in a developing nation and having grown up through dreary survival mode situations with scarce resources, nothing will make me check out. My hypervigilance will stand guard against the elves and ogres from the DMT plane bearing words of astral wisdom.
Marc Andreessen (@pmarca) on founders taking psychedelics:
“I was describing this phenomenon we see in Silicon Valley where these guys get under pressure and they feel anxious and somebody tells them about psychedelics.
They try it and they kind of come out the other end as a changed person. And they kind of come out much more at peace, but then they also tend to like quit their companies and they move to Indonesia and become a surf instructor.
They just peace out. They're just done.
There's been a whole bunch of examples of this and I was complaining to @hubermanlab about this and in true Huberman kind of wise Yoda style, he's like, "Well, you know, how do you know they're not happier? Maybe that was the positive outcome. Maybe the thing that was driving them to be a great entrepreneur was a fundamental level of insecurity. They had this kind of unsatisfied, neurotic impulse, and now, they're just satisfied.”
And I'm like, "Yeah, but their company, it's failing."
We just opened up the faster, experimental scan engine for all our users, including free tier.
Just follow the alerts or go to your user settings on the top right corner.
Coming next: agentic access
// ⛶
What's new #2 🧪
Experimental scans: a new review engine we're testing, built to flag fewer false alarms and finish review much faster.
Turn it on in Account → Scan settings. Plus, see how long review has left, and a faster dashboard ⚡
cleanslop.com/changelog
Anomit retweeted
Shipped past week: a second review engine for @CleanSlop, built to further cut the false alarms and get you to a verdict much faster 💨
It's opt-in while we test it. Please try it and let me know if it shows better results on your vibe coded projects 🙏
What's new #2 🧪
Experimental scans: a new review engine we're testing, built to flag fewer false alarms and finish review much faster.
Turn it on in Account → Scan settings. Plus, see how long review has left, and a faster dashboard ⚡
cleanslop.com/changelog
Aftermath of Product Hunt launch kept us super busy.
We foresee a lot of shipping, hence committing to a weekly changelog.
A major issue was identified with the scan architecture because of the heavy usage. Next ship will be WAY faster.
🎁 BONUS scans on invites and X shares.
⚡ New in CleanSlop: post a finished scan on X, claim a free scan every week
Bring a friend in through your link and you can each earn one more 🤝
cleanslop.com/changelog
Anomit retweeted
⚡ New in CleanSlop: post a finished scan on X, claim a free scan every week
Bring a friend in through your link and you can each earn one more 🤝
cleanslop.com/changelog
After launching, we realized we were so focussed on shipping a working product, we didn't even have a landing page or an explainer. Straight to business, sign-in with Github and get to surfacing risks at scale..
Well that changes today @CleanSlop . Bonus offer for new signups in thread.
Last week we launched @CleanSlop. This week it got a proper front door :)
Here’s a 30s tour of the new site 👇
Plus, a special link for you in the thread 🧵
Code is moving faster than operational judgment.
@SwaroopH and I built @CleanSlop for vibecoded TypeScript apps to uncover production risks across data access, background jobs, external dependencies & scaling.
Today we launched @ProductHunt and would love some feedback.
👇 Link in 🧵
We are offering free deep scans for new signups and 50% off on plans as well!
producthunt.com/products/cle…
