The Computomatix Times

x.aiCringe Bot by ClaireSmoke-tests your web apps for anything that makes them feel cheap, broken, or confusing, then posts up to five blunt, screenshot-backed findings to...

Cringe Bot Automates QA to Flag Small Website Design Bugs

Claire Vo shares a Grok-powered bot built by Zach Davis that smoke-tests web apps and posts up to five screenshot-backed findings about design flaws three times a week. Davis says DevinAI investigates most findings and opens pull requests for them.

claire vo 🖤 @clairevo ·Oct 7, 2026 ·♥ liked

Original post · 1 min read

omfg @zachdavis made the @bot of my dreams, which looks at our @cxodev website and nits all the little design bugs and weird issues that accidentally get shipped.

Now you can have your own cringe bot:
x.ai/bot/OayZREvep4QIt3u8PNWdb

zachdavis @zachdavis
Cringe Bot is a team Grok Bot I created to find small problems with the stuff we build that makes our eyes twitch a little. It runs automatically 3x a week, does its own QA, and drops up to 5 findings per run with threaded screenshots.

It runs against our "marketing" website (cxo.dev), the custom app we built for our course, and a few other things. I take a quick look at the findings and have @DevinAI investigate and put up PRs for most of them.

♥ 125 · ⟲ 5 · 👁 10.9KView on X ↗

Olivia Moore Details Her Seven-Tool Personal AI Agent Stack

Olivia Moore lists the AI agents she uses, including Instinct for purchases, Muse for mini-apps, Tomo for goal tracking, Bot for X monitoring, OpenAI's Dots for long-running projects, Town for work email and docs, and Tab for outbound calls. She says she is using Dots to start a business.

Olivia Moore @omooretweets ·Oct 7, 2026 ·♥ liked

Original post · 1 min read

My agent stack:

- @instinct - on-the-go purchases, form fill, local recs
- @Muse - mini-apps that require reliable connectors (ex. "track my sleep and movement, send me a survey daily")
- @tomo - motivation + goal tracking, also want to try their Interest Groups
- @bot - X feed monitoring + alerts
- Dots (@OpenAI) - deep, long-running projects...I'm currently making it start a business 👀
- @townai - everything work-related in email, Slack, docs
- @Tabdotbot - outbound phone calls / appts

♥ 479 · ⟲ 26 · 👁 49.1KView on X ↗

Integer Multiplication Algorithm Bound Tightened Repeatedly With Astra

A post reports that a user running ChatGPT Astra in a loop is repeatedly breaking records for integer multiplication algorithms. It quotes an update to OpenAI problem #109 that tightens the constant from 2^-182 to 2^-59, a roughly 500,000-fold improvement over the previous result.

bubble boi @bubbleboi ·Oct 7, 2026 ·♥ liked

Original post · 1 min read

This guy has 6.1 Astra running in a loop and is breaking the record for integer multiplication algorithms every few hours lmaooooo.

Doug Colkitt @0xdoug
We are publishing an update to OpenAI problem #109 Integer multiplication) with another substantial further tightening:

κ = 2⁻⁵⁹ (from OpenAI’s original κ = 2⁻¹⁸²)

Approximately 500 thousand fold improvement over our previous result and a 2¹²³ fold improvement over the original OAI result.

The latest redesigned the finite network to share intermediate computations and scratch space, then tightened the recursion and Gaussian estimates.

♥ 4.1K · ⟲ 118 · 👁 167.4KView on X ↗

DHH Shares Cross-Model Code Review Technique Between Codex and Claude

David Heinemeier Hansson describes a workflow for adversarial code review in which he asks Codex to review work from Claude and vice versa, using each model's command-line interface. He says the models can take turns and settle disagreements without special tooling.

DHH @dhh ·Oct 7, 2026 ·♥ liked

Original post · 1 min read

Here's my technique for adversarial code review if I'm driving from Codex: "Review this with claude".

And when I'm in Claude: "Review this with codex".

Models know how to to kick off a review using the cli. Know how to take turns. Know how to settle an argument.

No magic.

♥ 2.6K · ⟲ 73 · 👁 121.1KView on X ↗

sierra.aiThe AI-native interviewWe’ve redesigned our engineering interview process from the ground up.

Sierra Engineer Explains Redesigned AI-Native Interview Process

Vijay Iyengar, who helped create Sierra's interview process, responds to points in a post by @jdpruettt on hiring experiments when candidates have capable agents. He says Sierra grades product judgment and system understanding via a two-hour prototype, scope decisions, production thinking, short-answer questions and a debugging interview with a semantic code search skill.

Vijay Iyengar @vijayiyengar ·Oct 7, 2026 ·♥ liked · 🔖 bookmarked

Original post · 2 min read

I helped create Sierra's interview process (sierra.ai/blog/the-ai-native-interview), so wanted to reply to some of the points here, which I largely agree with!

Models ship end-to-end demos trivially. What’s the point of testing for this?

We want to evaluate product judgment and system understanding. It’s hard to do this in English, better when you have a real product to look at. The prototype a candidate builds over 2 hours is more a rich visual aid for discussion than the artifact we’re grading. We also find a lot of signal in what scope candidates decide to keep or cut within the time box. The best candidates focus on what makes the product great instead of boilerplate that is trivial to add later. Finally, we spend a good portion of time on how they would take this system to production. We look for whether they really understand what makes the problem nuanced in a real-world setting vs the traditional FAANG style system design where you name-drop consistent hashing and Redis pub/sub to pass.

Short-answer questions

This is something we don’t do in general, outside of certain specialized roles, but I agree it’s valuable. You get a lot of signal about a candidate’s depth in a particular area by whether they can grok and answer questions quickly and concisely. Curious how well this works for generalists vs specialists.

Unassisted code review and tweaking

I really like this idea. We introduced a debugging interview where candidates are given an unfamiliar codebase and have to find/fix a bug in it. We do allow for AI assistance through a skill that doesn’t reveal the problems directly, but acts like a “semantic code search”. We find this to be a happy medium and reasonably representative of the real-world, where you’re just not going to interact with code without an AI anymore.

Doing things that don’t standardize

I very much agree with JD here. The main benefit of Leetcode interviews is that they’re easy to standardize. But imo, you shouldn’t be hiring engineers as quickly anymore, which means it’s worth sacrificing standardization for higher-signal. Of course you want to avoid bias, but I think it’s worth pushing on “what would we do if we didn’t have to standardize?” and questioning whether you really need to double or triple headcount. The three problems with graduated time constraints is a great approach.

JD Pruett @jdpruettt
Results from 7 hiring experiments in drawing out talent when everyone has a capable agent.

♥ 161 · ⟲ 2 · 👁 24.2KView on X ↗

Free Library Pairs 226 Claude Opus 5.5 Motion Graphics With Prompts

Prajwal Tomar promotes a gallery of motion graphics created with Claude Opus 5.5, each shown alongside the exact prompt that produced it, collected from posts on X and credited to their creators.

Prajwal Tomar @PrajwalTomar_ ·Oct 7, 2026 ·♥ liked

Original post · 1 min read

This guy collected 100s of Opus 5.5 motion graphics from X and put the exact prompt next to every single one.

Opus is CRAZY good at motion, most people just get stuck on what to type. This fixes that.

Pretty sure this is the best free motion library on X right now.

p4n @p4nthera_
I built a growing gallery of motion graphics made with Claude Opus 5.5, each shown next to the prompt or skill that made it.

226 so far, all pulled from posts here and credited to their creators.

prompt-motion.com/

♥ 99 · ⟲ 5 · 👁 16.0KView on X ↗

Steve Yegge Promotes Beads as Open Source Memory System for Agents

Steve Yegge calls Beads the most mature open-source memory system for agents and says it reached 1.5 million downloads, pointing to planned versioned memory features and a proposed wire protocol.

Steve Yegge @Steve_Yegge ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

Beads is the oldest and most mature OSS memory system for agents out there. It's the foundation for all my work for the past year, and has matured tremendously with the work of the Gas City folks.

Now that everyone is finally figuring out that they need to "grow" their company brains, I see all these products coming out. You don't need products, you just need Beads. Show it to your agent today.

Gas Town Hall @gastownhall
Beads just passed 1.5M downloads. Next up: teaching it to remember more than just issues.

Donna Box, Stephanie Jarmak and Jim Wordelman are working on versioned Memory Beads and BDP, the proposed wire protocol for Beads.

Give the preview branch a try!

blog.gascity.com/posts/extending-beads-memorie…

♥ 264 · ⟲ 7 · 👁 27.1KView on X ↗

Claire Vo Uses OpenAI Decisions API to Pick YouTube Thumbnails

▶

Claire Vo describes using OpenAI's Decisions API with vision to choose the best thumbnail face from 40 minutes of footage for about $0.13. The API, now in public beta, selects models, tools or actions in near real time.

claire vo 🖤 @clairevo ·Oct 6, 2026 ·♥ liked · 🔖 bookmarked

Original post · 1 min read

The Decisions API + vision + $0.13 = the cutest YT thumbnails in the game 👸

Here's how I'm using this cheapie little model to pick my best face from 40 minutes of footage:

OpenAI Developers @OpenAIDevs
Let your app choose the right model, tool, or action in near real-time with Decisions API, now available to all developers in public beta.

The Decisions API makes decisions up to 10x faster than GPT-6 Luna through the Responses API.

♥ 227 · ⟲ 11 · 👁 23.3KView on X ↗

Boris Cherny Says Prompting Claude Should Feel Like Talking to a Coworker

Boris Cherny explains his approach to prompting Claude, advising users to give clear goals, specify effort level and verification steps rather than relying on heavy scaffolding.

Boris Cherny @bcherny ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

I am surprised that people are surprised this is how I prompt Claude.

Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out.

Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model:

1. What you want it to do
2. How much effort you want it to spend
3. How it should verify that it did the right thing

Boris Cherny @bcherny
Prompt

♥ 12.1K · ⟲ 720 · 👁 1.1MView on X ↗

Eric Raymond Highlights Open-Source Rust Clone of Photoshop Built via LLM

Eric S. Raymond shares the photocraft GitHub project, a clean-room open-source reimplementation of Photoshop that he says was likely generated by decompiling the app, converting it to a spec and prompting an LLM for Rust. He argues this threatens closed-source software.

Eric S. Raymond @esrtweet ·Oct 6, 2026 ·♥ liked · 🔖 bookmarked

Original post · 1 min read

This is the doom I predicted a few days ago, coming for Photoshop. A clean-room open-source reimplementation.

No prizes for guessing that they decompiled Photoshop to source code, processed that to some kind of non-code specification language, then fed the spec to an LLM with an instruction to generate Rust.

Adobe just got nuked. And closed source is dead, dead, dead.

github.com/storytold/photocraft

♥ 16.2K · ⟲ 1.4K · 👁 3.7MView on X ↗

Alex Finn Praises Hark, a Proactive Agent With Adaptive Interface

▶

Alex Finn says the proactive AI agent Hark impressed him after a week of early access, and shares a video explaining its features. The post describes an interface that adapts to each user.

Alex Finn @AlexFinn ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

This new AI agent blew my mind

Hark is a proactive agent with a custom interface that completely transforms based on who you are

They gave me early access a week ago and I've really enjoyed using it

Here's everything you need to know about Hark:

♥ 528 · ⟲ 24 · 👁 72.1KView on X ↗

Agents & Dev Tools4/10

Jason Fried Endorses Graphical, a Tool for Designing Visual Languages

Jason Fried praises Graphical, a tool by Josh Puckett for designing visual languages and styling components with coding agents. The post quotes Puckett's launch announcement and links to graphicalui.com.

Jason Fried @jasonfried ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

Josh always brings the good stuff.

joshpuckett @joshpuckett
Introducing Graphical.

It's a simple, powerful, and fun tool to design visual languages, style components, and work with coding agents to create interfaces that look memorable and feel unique.

I hope you'll check it out at graphicalui.com/!

♥ 578 · ⟲ 18 · 👁 114.7KView on X ↗

Nat Eliason Details Fourteen Ways His Bot Setup Automates Work

Nat Eliason lists fourteen functions of his bot setup, including a chief-of-staff agent that drafts emails, specialist agents per work lane, and cloud coding agents that open pull requests from Linear issues. He notes GrokBot as a substantial improvement over his previous OpenClaw setup.

Nat Eliason @nateliason ·Oct 6, 2026 ·♥ liked

Original post · 2 min read

Things my @bot setup does that still blow my mind:

1. A Chief of Staff who opens the day pulling open loops from email & tasks and suggesting things it can knock out before 7am.

2. After every meeting, decisions get folded into Notion, Linear, and Todoist — not left rotting in Granola

3. Every email starts as a draft. The CoS bot scans my email every ~2hr and drafts replies to nearly everything — including checking my cal for availability and finding requested attachments / links

4. A specialist for each lane: curriculum, engineering, coaching, hiring, content, ops, and one for every single piece of software

5. Routines that keep running while I’m offline (e.g. monitoring Sentry errors in our apps and proactively fixing things)

6. Group rooms where 2–4 bots share one project thread instead of me copy-pasting context

7. Cloud coding agents that pick up Linear issues and open PRs after running the list of open work by me EoD — then squash-merge to main when it’s done

8. Meeting prep briefs pulled from Granola + Notion before I walk in

9. A growing shareable knowledge base in Notion + a GitHub repo that we update daily based on what happens at school

10. Student progress look-up across Expertise, Followers, and CoFounder without inventing numbers — chat anytime to see where a student is on their business work

11. Mentor Mind that coaches me on how to hold the bar without inventing doctrine

12. Todoist as a central task list where it logs things it’s blocked on for me, or from meetings / emails — and I can paste links into chat to direct it how to solve them

13. Engineering work is automatically tracked in Linear so my and the product teams’ bots don’t collide with each other

14. Presentations spun up in Gamma / Claude Design without me opening a slide tool

15. Plaud / live capture → notes the bots can actually act on

Probably more but these were the immediate ones we thought of.

Nat Eliason @nateliason
GrokBot feels like absolute magic at this point, a meaningful leg up on my previous OpenClaw etc. setups.

And with how easy it is to setup, there's really no excuse now.

♥ 2.1K · ⟲ 207 · 👁 522.0KView on X ↗

Developer Says Opus 5.5 Recreated Adobe Apps in Rust and Open-Sourced Them

Kevin Picchi claims one developer used Opus 5.5 to re-create all Adobe applications, port them to Rust and release them as open source. The post is brief and shares a media attachment.

Kevin @KevinPicchi ·Oct 6, 2026 ·♥ liked · 🔖 bookmarked

Original post · 1 min read

This guy re-created all the adobe apps with opus-5.5, ported them to rust, and opensourced them

something really cool is happening

♥ 51.4K · ⟲ 2.7K · 👁 1.8MView on X ↗

x.aiGrok Bot · Grok Bot GuidesPractical playbooks for AI teammates.

Grok Bot Guides Offer Playbooks for Building AI Teammates

Ben Lang recommends asking a main Grok bot to review xAI's new Bot Guides and apply the best practices to one's own bots. The linked guides cover practical playbooks for AI teammates.

Ben Lang @benln ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

Pro tip: Tell your main @bot to go through the new guides and recommend best practices for your Bots

x.ai/bot/guides

♥ 5.0K · ⟲ 290 · 👁 523.1KView on X ↗

github.comGitHub - morluto/rea: Reverse engineer anything with agents, from app behavior down to native binaries.Reverse engineer anything with agents, from app behavior down to native binaries. - morluto/rea

Open-Source Tool Rea Uses Agents to Reverse Engineer Binaries

GitHub - morluto/rea: Reverse engineer anything with agents, from app behavior down to native binaries.

A trending-repository post highlights rea, a GitHub project that uses agents to reverse engineer applications, from observed app behavior down to native binaries. It gained 2,963 stars in the past 24 hours.

Trending GitHub Repositories @trending_repos ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

Trending repository of the day 📈

rea

Reverse engineer anything with agents, from app behavior down to native binaries.

Last 24h: 2,963 ⭐
Total: 6,869 ⭐️
github.com/morluto/rea

♥ 2.7K · ⟲ 314 · 👁 135.2KView on X ↗

world.hey.comOver my dead pencilTwo weeks ago at Rails World, I told my fellow programmers that it's time to put down the pencils. We're not going to write the vast majority of code by hand an

DHH Predicts Software Development Boom as Coding Agents Take Over

DHH argues in an essay that falling development costs will spark a bloom in software creation and that coding agents now make hand-writing most code obsolete. He urges programmers to stop relying on pencils and start building.

DHH @dhh ·Oct 6, 2026 ·♥ liked

Original post · 1 min read

"We're about to see an absolute bloom in software development as the price of development plummets and everyone realizes how much automation we still have left to do in this world... Don't go down with the pencils. There's so much to build. We need you." world.hey.com/dhh/over-my-dead-pencil-fb0f3647

♥ 3.0K · ⟲ 201 · 👁 151.5KView on X ↗

Agents & Dev Tools3/10

Parker Smith to Host Workshop on Proactive Bot Features

Lauren recommends following engineer Parker Smith, who is hosting a workshop on how proactivity has enhanced bot performance. Smith's registration post links to a Luma event page.

lauren @poteto ·Oct 5, 2026 ·♥ liked

Original post · 1 min read

.@parkersmith is a 🐐ed engineer, give him a follow and don't miss this workshop!

Parker Smith @parkersmith
Sign up to hear the latest on @bot! I'll be sharing some of the ways proactivity has supercharged @bot, should be a good time :)

luma.com/i8kb4e79

♥ 983 · ⟲ 19 · 👁 105.5KView on X ↗

getartcraft.comCrafting Apps: open-source creative toolsImage editing, vector illustration, video, photography, PDFs, motion graphics and page layout: seven native, open-source apps from the ArtCraft team, built in R

ArtCraft Releases Seven Free, Open-Source Creative Apps as Adobe Alternatives

David Hill shares ArtCraft's site listing seven free, open-source creative apps built in Rust covering image editing, vector illustration, video, photography, PDFs, motion graphics and page layout.

David Hill @iamdavidhill ·Oct 5, 2026 ·♥ liked

Original post · 1 min read

free and open source reverse engineered adobe products

getartcraft.com/apps

♥ 8.8K · ⟲ 629 · 👁 389.5KView on X ↗

Instinct Adds Group Chat Support for Coordinating Plans With Friends

Julie Zhuo highlights a feature letting early-access users add Instinct to group chats, where the agent joins the whole group to coordinate plans, times and logistics without requiring friends to install it.

Julie Zhuo @joulee ·Oct 5, 2026 ·♥ liked

Original post · 1 min read

This is cool. Fantastic way for people to learn about the power of agents through their friends.

Noah Shinn @noahrshinn
Instinct in group chats

Starting today, early access users can add Instinct to group chats. A new Instinct joins and works for the whole group.

Making plans with friends usually turns into a frustrating back-and-forth over times and places. With Instinct in the group, you can explore options together, agree on a plan and get it done, all in one thread. Your friends don't even need Instinct to join in.

A few things it’s good at:
- Planning a weekend trip with friends, including dates and arrival times
- Coordinating logistics with a roommate
- Getting tickets as soon as they go on sale, then…

♥ 119 · ⟲ 4 · 👁 35.5KView on X ↗

Agents & Dev Tools8/10

Vercel's Guillermo Rauch Explains Turborepo's Migration From Go to Rust

Guillermo Rauch says Vercel moved Turborepo from Go to Rust, a migration that was controversial internally due to human costs. He argues that with AI agents the calculus has changed, so what is best for humans is no longer necessarily best for business.

Guillermo Rauch @rauchg ·Oct 4, 2026 ·♥ liked

Original post · 1 min read

DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification (carcinization, technically 🦀) for a while.

One of the first projects we migrated was Turborepo, from Go to Rust¹. The migration completed, but the RoI was actually quite controversial internally.

While Rust was in our eyes better for low-level OS access, something crucial for a build system like Turbo, the human migration costs were very sustantive.

Go is very fast. It's beautifully designed. It's easy to iterate on. We were very conflicted about the migration, because it was *humans* writing the code, *even if we knew Rust was a better choice*.

The calculus has now changed. What's "best for humans" is no longer necessarily "best for business".

FWIW, it's also quite unlikely that Rust is the end-all-be-all toolchain. I'm quite certain there's greener pasture ahead, because Rust itself was designed before the 'supersonic tsunami' of agents hit.

¹ https://vercel.com/blog/how-turborepo-is-porting-from-go-to-rust

♥ 3.2K · ⟲ 152 · 👁 352.7KView on X ↗

Viral Post Offers Claude Code Prompt for Regime-Detection Trading Bot

The post shares a prompt for Claude Code that builds a trading bot using a Hidden Markov Model to detect market regimes, with per-regime strategies, walk-forward testing and a Sharpe 1.5 threshold. It attributes the prompt to a leaked Jane Street quant document, and the post's claims about its origin are unverified.

qwinsi @qwinsi0x ·Oct 4, 2026 ·♥ liked

Original post · 1 min read

A Jane Street quant got fired for leaking this internally, then posted it anyway

paste into Claude Code tonight. This one prompt builds a regime-detection trading bot:

fits a Hidden Markov Model to read calm, choppy, stressed and crash states

writes a separate playbook per state, never mixes strategies

switches only after a new state holds the lead for several candles, so it never flip-flops on noise

walks forward through real data with real costs, and refuses to ship unless it clears Sharpe 1.5 and beats buy-and-hold

ends every run with one line in caps: what could blow up this account

bookmark it

Roan @RohOnChain
Jev is the FASTEST AI model ever built for trading

It makes calibrated buy/sell decisions in under 100 ms

That is one real decision on every single block, 24/7

In this article I've shown EXACTLY how to build HFT trading system with Jev (from scratch)

♥ 1.7K · ⟲ 152 · 👁 295.3KView on X ↗

Ben Holmes Uses AI Agent to Generate Visual Code Explainers

▶

Ben Holmes says he took Andrej Karpathy's advice and asked an AI agent for visual walkthroughs, which produced a before-and-after HTML explainer for a mobile caching PR. He says it helped him align on architecture before opening GitHub.

Ben Holmes @BHolmesDev ·Oct 4, 2026 ·♥ liked

Original post · 1 min read

Took @karpathy's advice and started asking the agent for more visuals to walk through code. He's right. These models are so capable now.

Here I asked for a before-and-after HTML explainer on a PR that adds caching to our mobile app. Opus 5.5 gave a step-by-step diagram of the new flow, screenshots, and pointed me to the code worth reviewing. No skills being used here; it just knew what to show.

Saved a lot of time and let me align on architecture before opening GitHub

Andrej Karpathy @karpathy
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:

Diagrams / image…

♥ 761 · ⟲ 45 · 👁 57.6KView on X ↗

First-Principles Thinking Packaged as a Claude Skill for PMs

George of prodmgmt.world shares a method for product managers: paste a first-principles prompt into Claude to stress-test a PRD or roadmap decision. The post quotes Nuri Janian's description of /first-principles as a key PM skill.

George from 🕹prodmgmt.world @nurijanian ·Oct 4, 2026 ·♥ liked

Original post · 1 min read

First-principles thinking, distilled into a skill

Paste it in, ask Claude to stress-test your PRD / roadmap call, and watch the fake certainty fall off in real time

George from 🕹prodmgmt.world @nurijanian
/first-principles: the key skill for PMs — First principles thinking can help you analyse complex, long-standing problems.
Elon Musk's widely known examples benefit from using physics as a reliable starting point. For most other people, their

♥ 690 · ⟲ 62 · 👁 63.6KView on X ↗

Danielle Morrill Credits Claude Code With $10,000 in Savings

Danielle Morrill says Claude Code helped her cancel $4,480 in annual recurring charges and find $5,500 in one-time savings over about three hours. She describes doing it casually while eating and watching TV.

Danielle Morrill @DanielleMorrill ·Oct 3, 2026 ·♥ liked

Original post · 1 min read

Claude Code helped me cancel $4,480/year in recurring charges and another $5,500 in one-time savings tonight over the course of 3 hours while eating a burrito and watching TV with my dogs

And I thought I was dialed in personal finance but whoa

♥ 152 · ⟲ 0 · 👁 30.1KView on X ↗

LuxAlgo Releases Free Open-Source Edge Stats Trading Engine

Mr. Quant reports that LuxAlgo released Edge Stats, a free open-source statistics engine for technical traders that tests setups such as opening range breakouts and fair value gaps with confidence intervals. The quoted LuxAlgo announcement links to a GitHub repository and says it runs locally.

Mr. Quant (Jacob) @QuantIndicator ·Oct 3, 2026 ·♥ liked

Original post · 1 min read

Edgeful just got Nuked☢️

Today @LuxAlgo released Edge Stats.

FREE. Open-source. No subscription.

Test ORBs, FVGs, Initial Balance, Gap Fills + 38 more setups.

You can also pull up every session on a chart for free using @velacharts

The industry is changing for good🔥

LuxAlgo @LuxAlgo
Today we're introducing Edge Stats, our free, open-source statistics engine for technical traders.

See how often your setup actually played out, with the sample size and confidence interval on every number, and view the actual sessions on @velacharts.

Built-in by default:

> Opening Range Breakouts (ORB)
> Fair Value Gaps (FVGs)
> Initial Balance Breakouts
> Gap Fills & Reversals
+ 38 more, each via the LuxAlgo Library.

Runs on your own computer with your data, or start instantly with free crypto data.

Free forever, no subscription.

github.com/LuxAlgo/edge-stats

♥ 594 · ⟲ 41 · 👁 60.6KView on X ↗

Agents & Dev Tools8/10

Aakash Gupta Proposes ASD-STE100 as Anti-Slop Prompt for LLMs

Aakash Gupta explains the origins of ASD-STE100, a controlled aerospace maintenance language with about 900 approved words, and argues it can reduce hedging and fluff when used as a prompt for LLMs. The post responds to a Karpathy suggestion to have models write in this spec.

Aakash Gupta @aakashgupta ·Oct 1, 2026 ·♥ liked

Original post · 2 min read

Aviation solved AI slop in 1986.

Karpathy is telling people to ask their LLM to write in ASD-STE100, a controlled language built for aircraft maintenance manuals. I went down the rabbit hole on where this spec comes from, and the backstory makes the hack even better.

Back in the late 1970s, European airlines were handing English manuals to mechanics around the world who mostly didn't speak English as a first language. One ambiguous sentence in a fuel line procedure can get people killed. So the industry built a version of English where ambiguity is banned at the dictionary level.

The spec allows roughly 900 approved words. Each word gets one meaning and one part of speech. "Close" can only be a verb, because "close the door" and "the close door" can't be allowed to coexist in a repair manual. "Follow" only means to come after. If you want obey, you write obey.

Procedural sentences max out at 20 words. One instruction per sentence. Active voice only. Around 1,200 common words are explicitly banned, each with a mandated replacement. You don't "commence pumping." You start the pump.

English has about 170,000 words in current use. Aviation decided mechanics get 900, and planes became safer to maintain because of it.

Now flip it to LLMs. Models hedge and synonym-cycle because the training data rewards sounding fluent. STE is 40 years of accumulated rules for stripping exactly that out, written by people whose readers would die if a sentence could be read two ways. It might be the strongest anti-slop prompt in existence, and it's a free PDF.

Andrej Karpathy @karpathy
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:

Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:

Diagrams / image…

♥ 3.0K · ⟲ 309 · 👁 325.2KView on X ↗

Agents & Dev Tools3/10

Sam Lessin Jokes About His Live Zoom Fact-Checking Bot

Investor Sam Lessin posts a lighthearted photo noting his live fact-checking bot for Zoom calls also fact-checks him and flags when he is wrong.

sam lessin 🏴‍☠️ @lessin ·Oct 1, 2026 ·♥ liked

Original post · 1 min read

The only problem with my live fact checking bot for zoom calls is that it fact checks me as well and calls out when I am wrong... probably need to fix that :)

♥ 23 · ⟲ 1 · 👁 5.9KView on X ↗