i pulled the 120b weights earlier for this, but failed to make inference work so far

here is a dump of my understanding of the model arch to help invite critique:

WASHINGTON, D.C. (August 1, 2025) – The Corporation for Public Broadcasting (CPB) announced today that it will begin an orderly wind-down of its operations following the passage of a federal

After finding the homeschooling life confining, the teen petitioned her way into a graduate class at Berkeley, where she ended up disproving a 40-year-old conjecture.

image-1.jpg

Explore comprehensive NYC rental market analytics with real-time data, neighborhood insights, rent trends, and price distribution charts.

While we previously announced discontinuing support for all goo.gl URLs after August 25, 2025, we've adjusted our approach in order to preserve actively used links.We un…

Over the next 25 years, Africa is expected to add 900 million people to its cities, the largest wave of urban population growth the world has ever seen. How can the continent begin to prepare today?

Free CI/CD security audits for Erlang and Elixir projects, powered by SAFE and supported by Erlang Solutions.

A jury in Florida determined that Tesla should be held partly liable for a fatal 2019 crash involving its Autopilot technology.

After joining Mintlify (which acquired my previous company), I finally fixed a search bug that had bothered me for over a year as a user - the debounced search queries weren't being aborted, causing race conditions and poaor search quality. By adding an AbortController…

Major Australian tech company Atlassian has terminated 150 staff with a pre-recorded video, as the company pushes its AI-embedded customer contact solutions.

Build a bulletproof backup server with FreeBSD, ZFS, and jails. Complete guide covering encryption, security hardening, and multiple backup strategies for enterprise-grade data protection.

 

A blog about computers, functional languages, Lisp, and Scheme.

Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, “Manus”, and “Claude Code”…

Employee stocks will be canceled as part of the deal; former employees point to culture change across Philz Coffee.