oooooo, this could be fun to throw at some of the diff-detection stuff we are doing with monitoring @nickscamara_@nv_pavlichenko mentions in a comment below that they "[tried] to make an efficient model for inference on a GPU" π
my only questions is what tools are you using during training for web-data access (i.e. search, scrape, browser-use, etc) and how can I convince you to try @firecrawl ?
@WTTDOTM@NousResearch what scraping tool are you using? @firecrawl is the default if using the Hermes unified API.
I'm a little bias, but they're pretty great ;)
Today we're releasing Monitoring by Firecrawl π‘
Just enter a URL, describe what you want to track, and /monitor notifies your AI agent via webhook the moment pages or sites change.
Use up to 90% fewer LLM tokens by only ingesting what changes on a page.
The web wasn't built for AI agents. So we built Firecrawl.
- /search finds fresh, relevant sources from the web
- /scrape turns any URL into clean context for AI
- /interact automates clicks, pagination, and logins
Join 1,000,000+ developers connecting intelligence to the web.
Our PHP SDK is live π₯
Scrape any page to markdown, run live web searches, and navigate dynamic sites from PHP or Laravel.
composer require firecrawl/firecrawl-php
It's so hard to describe the vibe difference between Opus 4.7 and GPT 5.5 (for coding)
GPT is smarter and can unblock you, but it gets stuck in stupid ways and strangles itself with context sometimes.
Opus will go down the most insane paths and refuse to acknowledge obvious answers, but it understands intent better and has more taste.
Whenever I use one for more than an hour, I always reach to the other to "clean up".
Best part? All of this changes every few weeks π