Proof Of Build strong opinions · cited sources
  • Home
  • About

X's hosted MCP turns the API back into a product

On June 30, 2026, X's developer account announced a hosted X MCP: connect Grok, Cursor, or any MCP-compatible AI tool to the X API "without any setup." The pitch is that agents now have access to

04 Jul 2026 · 3 min read ·hosted X MCP

Claude Code will now build and host a live page from one prompt

Two weeks. That's how long Artifacts stayed a Team-and-Enterprise beta before Anthropic pushed it to Pro and Max on July 2. The feature was announced June 18 as interactive pages built from your session, a PR walkthrough or

03 Jul 2026 · 3 min read ·Artifacts in Claude Code

Fable 5 is back, and Anthropic's own tests say the ban never needed to happen

On June 12, the US government applied export controls to Claude Fable 5 and Mythos 5. Because the order took effect immediately and Anthropic had no reliable way to verify nationality in real time, it pulled both models for everyone.

02 Jul 2026 · 4 min read ·Fable 5 export controls

Anthropic's three-agent loop is the lesson. The 40-minute app is the distraction.

Anthropic engineers ran a live demo building a full app from scratch in roughly 40 minutes, using three agents in a loop: one plans the work, one builds it, one judges the result, cycling until the app actually works. The

30 Jun 2026 · 4 min read ·agent loop

Claude Tag lands in Slack. The loop is what decides if delegation works.

Anthropic just put Claude inside Slack as something you can @-mention. Claude Tag adds Claude as a team member with access to the channels and tools you pick, so you tag it into a thread, hand off a task, and

30 Jun 2026 · 3 min read ·Claude Tag

GLM-5.2 "beat Claude" — but Semgrep's own harness still won by 20 points

The number everyone quoted is the least interesting one Semgrep ran an open-weight model against the same IDOR benchmark it uses on frontier coding agents, and GLM 5.2 scored 39% F1, beating Claude Code at 32%, for roughly $0.

29 Jun 2026 · 4 min read ·GLM 5.2

Google's free 8-minute agent lesson, and the recycled pitch selling it

Anatoli Kopadze told a 706,000-view audience that Google just dropped a free 8-minute lesson on building your first AI agent, called it "the clearest explanation of AI agents and loops you'll find anywhere," and added

29 Jun 2026 · 3 min read ·AI agent

DSpark: DeepSeek published the inference trick its rivals keep secret

DeepSeek just dropped DSpark, a speculative decoding method for its V4 Flash and Pro models, and it didn't stop at a paper. It shipped the draft model and the framework to train your own. [1] That second part

29 Jun 2026 · 4 min read ·speculative decoding

The Viral "AI Engineer" Skills List Is Two Jobs, Not One

A skills list went viral three times A list of roughly twenty-two things you should "learn" to be an AI engineer has been circling X for a month. The version making the rounds this week pulled 221.4K

29 Jun 2026 · 3 min read ·AI engineer skills

Plan, build, judge: why the agent loop beats the smarter model

Engineers from the team behind Claude Code published a 40-minute video building a full app from scratch, and the structure is the entire point: three agents in a loop. One plans, one builds, one judges, cycling until the app actually

26 Jun 2026 · 3 min read ·agent loop
Page 1 of 4 Older Posts →

Proof Of Build — AI tools and workflows for builders. Strong opinions, every claim sourced — receipts included.

Every claim on this site maps to a verifiable source. Built with an AI pipeline, reviewed by a human, receipts included.