Information hub for our project training the largest possible historical LLMs. - DGoettlich/history-llms
*If you haven't tried DQX for data quality checks, you should! First released almost a year ago, it quickly became a default for Databricks users.
You can validate your data using json, yaml, or Python, and quarantine data that does not pass the checks. Below an example of an yaml file.
Check ou...
Reverse-engineering Claude Code reveals why it performs differently from other agents that use the same Anthropic models. The answer lies in sophisticated context engineering and tool orchestration hidden beneath the surface.
Story points are hard to understand and hard to use well. Ease your burden! All will be explained.
*You ask a language model to help draft a paragraph. It gives you something that feels exactly right. You lightly edit it and move on. What you don’t see is that the substance and flow of the paragraph closely track a paper you have never read, absorbed into the model during training and now influen...
May 23, 2019 ... This is RonJeffries.com, the combination of new articles, XProgramming, SameElephant, and perhaps even some new items never before ...
In which a mid-career developer discovers that LLMs are just the latest swing of a pendulum that’s been moving since before computers…
A CLI-based, flat-file issue tracker for humans and robots. 🤖 - hmans/beans
This page automatically loads score data from several LLM leaderboards and shows an interactive chart that tracks how top benchmark results have changed. The chart groups benchmarks by category, hi...
*#Platform teams are often caught up in lofty promises and forget some crucial details that are sure to come back to haunt them:
- Operational Model
- Tenancy Model
- Ownership Model
Platforms usually sit on top of cloud services, meaning the cloud provider handles ops. However, for developer...
In: URL https://kellerjordan. github. io/posts/muon (2024). [132] Praneeth Kacham, Vahab Mirrokni, and Peilin Zhong. “PolySketchFormer: Fast ...
I’m hanging out in Sydney with my esteemed co-author and co-conspirator Gene Kim today; we flew in to conduct Vibe Coding workshops and…
A better and intuitive way to organize notes in Obsidian.
Spec-driven development (SDD) for AI coding assistants. - Fission-AI/OpenSpec
Aider uses a map of your git repository to provide code context to LLMs.
Helm, the Kubernetes application package manager, has officially reached version 4.0.0. Helm 4 is the first major upgrade in six years, and also marks Helm's 10th anniversary under the guidance of the Cloud Native Computing Foundation (CNCF). The update aims to address several challenges around scal...
Beads continues to grow momentum. When my old friends start stumbling across it independently, I know it’s going viral.
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
_It is always possible that dev team did all the code right, good product and ... -- https://www.eiu.edu/armyrotc/docs/adp6_22.pdf · hapless 4 months ago ..._
Browsing feels broken without these open-source tools.
Google Antigravity - Build the new way
Microsoft addressed a flaw in Azure Bastion, that allows attackers to bypass authentication and escalate privileges to administrative levels.
*🚀 Just stumbled upon “Introduction to Machine Learning” by Laurent Younes and wow, this one is a mathematical masterpiece! 🔥
From the ground up, it builds a rigorous foundation for understanding ML through linear algebra, probability, optimization, and statistics — all leading to the algorithms w...
A very simple static homepage for your server. Contribute to bastienwirtz/homer development by creating an account on GitHub.
*NVIDIA just made their best AI models free.
99% of developers have no idea.
While you burn cash on OpenAI credits... NVIDIA open-sourced Nemotron. Their entire agentic AI family 🤯
Free Models That Actually Ship: • Nano: Runs on your laptop • Super: Single GPU beast • Ultra: Multi-GPU monster
...Are Internal Developer Platforms like Backstage merely a hyped topic that will be forgotten in a few years?
Contribute to Jedward23/Tmux-Orchestrator development by creating an account on GitHub.
We show that the scaling laws which determine the performance of large language models (LLMs) severely limit their ability to improve the uncertainty of their predictions. As a result, raising their reliability to meet the standards of scientific inquiry is intractable by any reasonable measure. We ...