Arnav Gupta

Make your agent more secure by using this open-source framework called Immunity-agent v1.2.0 is out 👇 Now learns from its own sessions 1. Scoped agent: synthesizes minimal task‑specific rules at session start 2. Session learning: mines recurring commands and proposes candidate rules for human review 3. False‑positive & evasion: flags repeated dismissals and detects structural rewrites, storing signals in SQLite

@KenLin1985 Track 444 🏁 Fastest Lap: 6.550s ▇ 🔗 Race against me at hotlapdaily.com/?raceId=4cc4a4…

Spent just 2 days vibe coding and already have a playable kart racing prototype. AI has reached a point where even building 3D games feels fast and fluid. I used Cursor (Opus 4.7) with Three.js plus CC-licensed assets. The plan is clear. This will go live on Karts․com as a real-time multiplayer racing game. Multiple tracks, different characters, and constant expansion. The first track is inspired by Santa Monica Pier. Next step is more advanced tracks, boosts, slopes, and deeper mechanics. Building a game and watching your ideas come to life piece by piece is insanely fun. #GameDev #DomainDrivenDevelopment

@dreadnode What made the agent decide to pull and decompile specifically the Cosmos DB scaler? was it random or did it target high value msft components?

In less than 20 minutes and under $2, we used our .NET reversing capability to run a SAST scan of Azure Cosmos DB in the Microsoft Container Registry (MCR), surfacing a high severity vulnerability in the now-deprecated database. 🆕 Model: Moonshot AI - Kimi K2.6 ⏱️ Task/agent runtime: 19 mins 26 secs 🪙 Tokens: ↑ 3124.0k · ↓ 33.3k 💰 Cost: $1.97 Vulnerability Overview: When using managed identity auth, it calls an internal token service over HTTPS, but the TLS certificate validation callback is tautological — it checks if the server cert's thumbprint matches any cert in the chain, but the leaf cert is always in its own chain, so it always passes. Watch the video to see how we ran it within our TUI. Install Dreadnode and try out the .NET reversing capability: ➡️docs: docs.dreadnode.io/tui/capabiliti… ➡️command: ray.so/gyrc2qB

@GithubProjects github.com/Ar9av/PaperOrc… to generate full fledged research paper basis on your experiments , it uses PaperBanana

Paperbanana: generate research diagrams and plots from text

@KanikaBK github.com/Ar9av/obsidian… simpler yet easier

ANDREJ KARPATHY DESCRIBED A KNOWLEDGE SYSTEM THAT GETS SMARTER THE LONGER IT RUNS. Someone built the whole thing inside Obsidian. 100% FREE. Your notes become a WIKI THAT WRITES ITSELF and compounds like interest with every source you add. Here is what is actually going on. Karpathy dropped a gist a while back describing something he called the LLM Wiki pattern. The idea was simple but the implication was wild. Instead of asking an AI a question and getting an answer that disappears when you close the tab, you use the AI to build and maintain a persistent knowledge base that gets richer every single time you add something to it. The 50th source you add does not create 50 isolated notes. It creates 50 notes woven into a mesh of 500 cross-referenced connections. Nobody built it properly. Until now. It is called claude-obsidian. You install it in Claude Code, open your Obsidian vault, type /wiki, and the whole thing sets itself up. From that point forward the AI does the organizing, the cross-referencing, the contradiction flagging, and the filing. You just drop sources in and ask questions. - /wiki ingest builds structured wiki pages from anything you throw at it, URLs, PDFs, articles, notes - every new page gets cross-referenced against everything already in the vault automatically - /autoresearch runs an autonomous research loop, configures depth and sources in one file, produces full wiki sections on its own - a hot cache file stores the last session context so you never spend 10 minutes re-explaining what you were working on - /save turns any Claude conversation directly into a permanent wiki page - /canvas builds a visual knowledge graph connected to your vault The creator tested /autoresearch on AI marketing automation. Three rounds produced 23 wiki pages. Two of those pages became blog posts that now rank on page one. Every note app, every second brain system, every Zettelkasten method all have the same problem. They only work if you maintain them. And nobody maintains them. Notes go in, connections never get made, and six months later you have a digital graveyard. This solves that. The AI maintains it for you. You just add things. 358 stars already. MIT license. Free forever. Karpathy described the pattern. Someone spent weeks turning it into a tool anyone can install in two minutes and just use. I still do not understand why this is not the most talked about repo this week.

@Amank1412 I play hotlapdaily during that time. Track 437 🏁 Fastest Lap: 5.100s ▇▅▆▇▆▅▅█ 🔗 Race against me at hotlapdaily.com/?raceId=2cf0f6…

Someone built a transparent Mario game that runs OVER IDE so can play while waiting for Copilot to write code.

Does anyone know where can I buy a real parachute in Bangalore?

@heyysomu08 @fal they reached back after fixing, within 24 hrs

@_ar9av @fal I am facing this same issue. How to get it fixed any idea ?

Hey @FAL, I'm getting an "Admin lock" on my account for no reason, even after topping up. Support email has been sent, but I’d love to get back to work. Can you help me out? #falai #buildinpublic

@DoctorYev simplified security prismor.dev

pitch me your company in 2 words ((I'll re-post my favorites))

@alxmthew @berryaiplushies @grok have we gone beyond the inflection point?

Introducing Berry (@berryaiplushies): the first anti-sycophantic AI companion in a stuffed animal. I'm only 17 and we just went viral on TikTok, raised money from incredible people, and now we're shipping to thousands of teens by Christmas.

@victormustar Track 434 🏁 Fastest Lap: 8.850s ▇ ▂ 🔗 Race against me at hotlapdaily.com/?raceId=f53e95…

GLM-5.1 > Claude Code (Opus 4.6)? I'm tripping or CC has become very bad but built a Three.js racing game to eval and it's extremely impressive. Thoughts: - One-shot car physics with real drift mechanics (this is hard) - My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen - 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters - All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio! - Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed You are going to hear about this model a lot in the next months - open source let's go 🚀🚀

@YashikaChugh4 @higgsfield Whats better kling or higgsfield?

sat night plans w seedance 2.0 n @higgsfield

thanks obsidian-wiki #obsidian #wiki

@aiwithjainam github.com/Ar9av/PaperOrc…

@aiwithjainam If you are into research and writing papers you all should checkout this repo based off PaperOrchestra paper by Google for writing submission-ready LaTeX paper. Just plug to your agent and ask it to create the paper based off this project.

This is the research assistant I wish I had in grad school. Claude Scholar plugs into Claude Code and handles everything around your actual thinking: Literature review. Experiment analysis. Paper writing. Citation verification. Rebuttal drafting. Post-acceptance prep. Every session compounds it writes to Obsidian and Zotero so nothing gets lost between runs. 2.1k stars. Free. MIT License. github.com/Galaxy-Dawn/cl…