Assah Bismark

It's better to be dead than to be alive and not know why.

@zeddotdev just quietly killed all existing agent harnesses

Warp is now open-source.

@superdoteng Think @superset_sh already tried this.

Meet Superconductor. A native macOS app for agentic engineering, built to go fast. No Electron. No Tauri. 100% Rust. Manage all of your coding agents without friction. We're in Alpha: super.engineering

@FactoryAI too buggy will pass

Today we're releasing the Factory desktop app. A native interface for autonomous AI agents that work across every part of your software business.

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

introducing superset the IDE for the AI agent era stop waiting on coding agents run them in parallel

Link to the repo if you want to give it a try: github.com/AssahBismarkab…

What does it take to build an accurate AI agent for automatic code review? I ran an experiment to find out, meet Snif understands your codebase and provides evidence-backed findings that survive testing and benchmark filtering

The more we know, the less certain we are.

@ThePrimeagen The model 😂

I cannot stop thinking about Anthropic today for some reason 1. They claim that they are a company that prioritizes safety first and that they are creating a model responsibly 2. we learned from the code leak that anthropic employs deceptive techniques by calling fake tools to throw off distillers... Is this lying pattern built into claude or just the harness running claude? What else are they lying about? I am a bit more concerned now.

@cursor_ai @kentcdodds Will pass, the vendor lock-in on free tier is still hard

We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.

@jaydwivedi_ authors do write professionally not necessary ai gen.

ohhh man, not another author using AI 😭

@LexnLin @perplexity_ai They have one of the worst UIs I have ever used so far..

what the actual heck is @perplexity_ai's UI doing

@Lovandfear IMO thinking from first principle is beyond pattern recognition.

Pattern recognition is the highest form of intelligence.

you're probably underestimating how crazy things are

Andrej Karpathy on autoresearch with an untrusted pool of workers: "My designs that incorporate an untrusted pool of workers (into autoresearch) actually look a little bit like a blockchain. Instead of blocks, you have commits, and these commits can build on each other and contain changes to the code as you're improving it. The proof of work is basically doing tons of experimentation to find the commits that work." The idea that distributed & permissionless autoresearch ~= proof-of-useful-work remains a high-level intuition for now, but it is extremely intriguing to say the least. Someone needs to take this further. See QT for more on what's missing.

@atmoio AI doesn’t make CEOs delusional. It gives delusional CEOs a tool that validates their delusions faster.

@getsome_air Great product @getsome_air. The agentic features and multi-agent orchestration are genuinely well designed Two things that would make it ready: memory/performance optimization and AWS Bedrock support

No single AI agent excels at every task. Air lets you switch between Codex, Claude Agent, Gemini CLI, and Junie, so you can use the right agent for each job. Try Air for free: jb.gg/4dhmrw

@kunoo Bro is charting from metaverse

This is who you're trading against.