Show HN: Agent Draw: An agent draws while you talk, built on TLDraw(techstackups.com)

48 points by jameswhitford 3 months ago | 15 comments

MCP is great, you're just using it wrong(techstackups.com)

8 points by ritzaco 7 months ago | 5 comments

Blowing up my compile times for dubious benefits(claytonwramsey.github.io)

88 points by Tyrubias 3 years ago | 26 comments

Laravel raised money and now injects ads directly into your agent(techstackups.com)

166 points by mooreds 6 months ago | 97 comments

I started a devblog about mixing SwiftUI and C++ to make a Twitch app(kulve.org)

25 points by Swifcheese 1 year ago | 3 comments

Zuckerberg 'Admits' Meta's Layoffs Were Ineffective(eshumarneedi.com)

165 points by ExMachina73 3 months ago | 146 comments

GLM 5.2 beats Claude in our benchmarks(semgrep.dev)

1038 points by jms703 4 months ago | 476 comments

Semgrep blog post reporting that the GLM 5.2 model outperformed Claude in Semgrep's cybersecurity benchmarks.

GLM 5.2 Is Out(twitter.com)

701 points by aloknnikhil 4 months ago | 413 comments

Announcement that Z.ai released GLM-5.2, a coding-focused model with a 1M-token context window, with an MIT-licensed open release planned for next week.

GLM-5.2 is a step change for open agents(interconnects.ai)

344 points by vantareed 4 months ago | 197 comments

Nathan Lambert's Interconnects post arguing that the GLM-5.2 model marks a capability threshold for open-weight agentic AI.

GLM 5.2 and the coming AI margin collapse(martinalderson.com)

641 points by martinald 3 months ago | 412 comments

Blog post by Martin Alderson, first of a two-part series arguing that open models like GLM 5.2 will drive a collapse in AI provider margins.

Getting the most out of Opus 5.5 in Claude and Claude Code(claude.dev)

192 points by saikatsg 23 days ago | 132 comments

A playbook blog post by Addy Osmani on prompting Claude Opus 5.5, steering long runs, and checking results in Claude apps and Claude Code.

Opus 4.5 is not the normal AI agent experience that I have had thus far(burkeholland.github.io)

797 points by tbassetto 9 months ago | 1203 comments

Burke Holland's blog post arguing that Anthropic's Claude Opus 4.5 is a step change in AI coding agent experience.