Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 1,015 posts.
Hey! Before we go any further — if you want to support my work, please sign up for the premium version of Where’s Your Ed At, it’s a $7-a-month (or $70-a-year) paid product where every week you get a premium newsletter, all while supporting my
Prompt Engineering, also known as In-Context Prompting, refers to methods for how to communicate with LLM to steer its behavior for desired outcomes without updating the model weights. It is an empirical science and the effect of prompt engineering methods can vary a lot among models, thus requiring heavy…
In one of the side plots to The Lord of the Rings , two of the Hobbits attempt to rouse Treebeard—a wise but ponderous sentient tree—to defend his forest from an army that is cutting it down. The problem is that Treebeard operates at a very different speed than the Hobbits. It takes him a full day simply to say hello…
In this post, I’ll iteratively optimize an implementation of matrix multiplication written in CUDA.My goal is not to build a cuBLAS replacement, but to deepl...
The field of generative AI is evolving quickly. It brings compelling opportunities to improve developer productivity, but it also brings risks: to reviewer burden, to safety and security, and to intellectual property.
Named tensors for better deep learning code.
Drawing on five years of Pew Research Center surveys, here are 13 findings about how Americans use and view AI, and where they see promise and risk.
Today we’re announcing $110B in new investment at a $730B pre money valuation. This includes $30B from SoftBank, $30B from NVIDIA, and $50B from Amazon.
The “Hey Siri” feature allows users to invoke Siri hands-free. A very small speech recognizer runs all the time and listens for just those…
You should always change doors when playing Monty Hall
The numbers clearly show this is a pointless distraction for the climate movement
[LinkedIn discussion, Twitter thread]
Vibe coding is having a moment. The term was coined by Andrej Karpathy just a few weeks ago (on February 6th) and has since been featured in the New York …
For LLM of equivalent performance, the inference cost is decreasing by 10x every year. What cost $60/million tokens in 2021 costs $.06/million tokens today.
We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GPT-2 and GPT-3.
On the national, local, and personal level
An Architect model describes how to solve the coding problem, and an Editor model translates that into file edits. This Architect/Editor approach produces SOTA benchmark results.
A methodology for measuring the energy, emissions, and water impact of Gemini prompts shines a light on the environmental impact of AI inference.
Happy birthday to me! Recently, lots of people have been asking me what I think about IIT—no, not the Indian Institutes of Technology, but Integrated Information Theory, a widely-discussed &#…
New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators
When AISLE tested Mythos's showcase vulnerabilities on small, cheap, open-weights models, most found the same bugs. Here's what that means for cyber.
I presented an invited keynote at the AI Engineer World’s Fair in San Francisco this week. This is my third time speaking at the event—here are my talks from October …
Practical guidance from Anthropic on building reliable AI agents, from simple composable patterns to fully autonomous systems.
We use GPT-4 to automatically write explanations for the behavior of neurons in large language models and to score those explanations. We release a dataset of these (imperfect) explanations and scores for every neuron in GPT-2.
I feel like vibe coding is pretty well established now as covering the fast, loose and irresponsible way of building software with AI—entirely prompt-driven, and with no attention paid to …
llama.ttf is a font file which is also a large language model and an inference engine for that model.
Accessing Wolfram|Alpha's computational knowledge with ChatGPT--an ideal combination of precise computation with human-like expression of ideas. Stephen Wolfram explains how.
