aryan

@GaddipatiHarsha how do you find the numbers?

Free game for anyone trying to close deals via cold outbound

@dharshinimaru fire

We got tired of broken clinical trial systems, so we built Adam Biotech. Preclinical testing wasn't built for the speed AI designs drugs at now. 90% of drugs that pass preclinical still fail in clinical trials. We're not slowing drug discovery down to fix that. We're building 3D-bioprinted human tissue, on demand, engineered to catch the failures your animal models and 2D models miss. adambiotech.com

@GaddipatiHarsha bro lets hoop sometime

Real day 1s knew I used to weight 100 pounds at 5’ 10 and play basketball. Crazy that this is my profile photo for AI 😭

@soleil_colza_ @fdotinc @k_taro56v2 @arkorlab @vllm_project yoo this is sick. i actually built a scraper to scrape the best spot instances based on workload intensity so super relevant addition

We created Haru, A vLLM-native GPU orchestrator that turns unreliable spot instances into near-100% uptime. Here's how it works 🧵

@biraj21_ really good

is this good for a new hacker news account 🤔

goat panel @FarzaTV

@aritro_bh i love seaweb!

Your AI agent isn't dumb. It's just trying to read a website built for the human eye.

@GaddipatiHarsha @slashyemail obsession reference 👀

changed our logo today. spent two years telling myself branding didn't matter because the product did. turns out both are true. it just took me a while to admit the second one. new slashy. same obsession.

@_ar9av super cool product!

Today we are launching Prismor Production AI agents operate autonomously with all sensitive access but lack the critical visibility of their actions Prismor is an open-sourced control plane for AI agents which lets you: - redact secrets so agents dont read them - secure supply chain package consumption - skill and mcp scanning for prompt injection - scan and fix vulnerabilities (safely and validated) - all agent executions in a local self-serve dashboard About 3000 developers are already using it and we'd love for you to give it a shot

warner bros gonna yoink this and do numbers

@GaddipatiHarsha @interaction @slashyemail LMAO this is hilarious

Poke tbh isn't that useful. But I find the below usecase pretty nice. Is why I recommend people to use @interaction along with @slashyemail Slashy can't order you uranium, only can make sure you stay on top of your inbox and calendar.

@joypbuilds where are you working out of? 👀

can’t believe no one’s grinding on a sat 4th jul morning smh

these guys are straight cooking

what a game

@soleil_colza_ @fdotinc @k_taro56v2 @arkorlab yoo hella cool

Introducing Arkor: Your own LLM endpoint that improves while you sleep 🐑💤 Get your model in 3 clicks, swap your existing endpoint, and let it train from production logs. I’ll be sharing more about it in daily videos! DM if you want your own model for your product.

@joypbuilds dope life journey

hi i'm joy, former concept artist in games from startup to AAA now i'm a tech founder building in sf here's my story

@hahnbeelee did you hire an ai?

our sales guys are now sending me html files

@v1hns crazy bro 😭

wtf was the point of fable bro 😭 paying double in credits for an evaluation on whether fable will write a line of code which says no 80% of the time U can’t even say hi bro 😭

@ducnguyen67201 super helpful for not blowing my monthly budgets out the water!

We built the firewall for AI agent spending. INTRODUCING TrustLoop. Give your AI agent a card and it can burn $800 overnight — no approval, no limit. TrustLoop puts every payment through a policy first: • Set a hard spending cap per agent • Auto-approve trusted charges (compute, search) • Pause + ask you on any new vendor • Block anything over budget — no money moved • Full audit log of every decision • One line of config, works with any agent An agent with no spending limit is just a blank check. TrustLoop draws the line. First 10 design partners get it free 👇 gettrustloop.app

@idyeetya1 preciate it twin

@ai_singhal another banger tweet

Your agent works in staging but breaks in prod. Every time. We built an MCP that replays REAL production sessions against your changes before you ship. Supports Python, TS, Go (more languages coming soon) And best of all, it lives in your fav code editor! runmirrors.com