The heady mix of exhaustion and accomplishment is real today. The second major, 100% agentic, release of @CleanSlop is on Product Hunt today. It supports Stripe's @Link agent identity to attest to the validity of an agent. We are among the first few products at the moment to integrate it throughout our workflow. And cleanslop.com is a first-class agentic resource at this point. Just point your agent or assistant to it in the context of the codebase you want to work on. Also, definitely a good time to clear out recurring queries and refrains that we keep running into. (blogs and docs will be up once the dust settles from handling the influx from this release) - This is a deterministic risk scanning and surfacing engine that has been trained on 25+ categories of where and when things can go wrong. How do we know where to look? Just check the scale of things we have worked on in the last decade. - Techincally, it is static analysis. We haven't gotten to the runtime yet. And it is currently monofocussed on vibecoded webapps that are typically generated on Next.js/TS/Supabase sort of stack. iOS support coming soon. - The engine is continually trained, updated and refined on widely available public corpora of codebases as well as synthetically generated ones. We can promise our results and findings will only get better with time, not regress. - WE ARE NOT A LLM WRAPPER AND YOUR CODE DOES NOT GET SHIPPED TO RANDOM LLM PROVIDERS. Can not stress this enough. We have a ZDR in place if you don't want to include your codebase for training purposes, and when it comes to multi-phased scans where the scanner surfaces findings it is not confident on, only slices of callgraphs, import trees etc are consulted with decision models like @typesafeai Jev or @Cloudflare Clef. - This is NOT a security audit. This is not a package or collection of SKILL.md files that require an LLM subscription from you. This is definitely something that will bring to attention what will break when internet scale traffic and users hit your app.

Decentralization was supposed to solve the fiascos that have come out of centralized dependencies. Filesystems, package repos, mirrors, name roots (I recall Handshake Protocol). Instead we let zyn coke addicted Wall St. quant imports to ruin the show with their casino greed BS.

Google has refused to acknowledge issues with their Pixel 8 Pro WiFi for almost a year. And I continue seeing major system updates pushed at least once in a month, sometimes twice. At this point, it has become an unusable brick. Planned obsolence is a real thing.

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…

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.

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.

Uh...phrasing?

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.

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 // ⛶

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.