New practices require new tools. While crypto natives build the trust layer for agents (eip 8004), explicit social graphs find their way as filters and defensive mechanism against ai slop and ddos-like PRs in code repositories

0/ ERC-8004, the standard for universal AI agent identity, reputation, and verification, is now live on Ethereum Mainnet. With the ERC-8004 standard, AI agents are accountable economic actors. Here are 5 unlocks that ERC-8004 gives to builders, and how to integrate today.

undefined creator skill coming to skills.sh in 3, … 2, …, 1

the industry is moving in an interesting direction with semantic search alternatives to grep for coding agents. there's mgrep by mixedbread there's semtools by llamaindex now there's (multi-vec) colgrep by lighton very cool to see these advancements. congrats to

This is a triple hit combo: 👊RLM for a new way of working with a large context 🤜DSPy for opinionated way of building systems with llms, not chaining strings with prompts 🦶Modal for serverless infra, sandboxes Cc Charles 🎉 Frye

Vibes arbitrage - new hedge fund activist strategy

Most enterprise software sales teams are built for comfort. ElevenLabs built theirs for output. Here’s the ruthless enterprise sales playbook they’re running 1. The 20x Rule Forget 6–8x quotas. At ElevenLabs: → $100k base = $2M quota → ~80% of reps hit it Translation:

welp, it was fun while it lasted folks

"Optimize everything" is a bold statement but this team has already shipped important building blocks Thanks for adding another task to my backlog 🥲

Running a typical services agency is often a brutal fight for survival. Many tech firms fall into the “selling developer hours” trap - margins get crushed, and the business becomes painfully sensitive to market swings. x.com/tomik99/status…

Today in alternative universe: a human releases None Banana 2 🍌

Anthro peak

HUGE BREAKING NEWS: Why OpenAI and Sam Altman could say yes where Anthropic couldn't. Hint: it's architectural. OpenAI can say yes while Anthropic can't BECAUSE OF HOW THEY ARE BUILT. HUGE analysis of all of X and everything is going on between OpenAI and Anthropic:

When production gets commoditized clarity of the communication becomes the next 10x leverage. Whoever explains the problem better than users in their own minds gets a seat at the table and gets invited to the “uv add “ stage of engagement

implemented DSPy's optimize anything as a MCP server and Claude Code Skill. Just: evaluate → reflect → improve → repeat github.com/rachittshah/op…

"AI agents will replace manual trading." Yeah right I'd love to see an AI agent sell the bottom, lever into a revenge trade, get liquidated, and then reenter the trade with double the size before closing for a catastrophic loss