1081
It’s so hard to finish an idea that is not yours and is just suggested by AI
Everyone is using Obsidian for AI, or wants to use it to become more productive. But I think it's a dead end.
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 3,091 posts.
1082
1083
LLM Agents Are Simply Graph – Tutorial for Dummies
Ever wondered how AI agents actually work behind the scenes?
1084
Neural Networks, Manifolds, and Topology
Recently, there’s been a great deal of excitement and interest in deep neural networks because they’ve achieved breakthrough results in areas such as computer vision. 1
1085
Training an LLM in Swift, Part 1: Taking matrix mult from Gflop/s to Tflop/s
10 implementations of handwritten matrix multiplication: from plain C and Swift through to Metal
1086
What's the best programming language for coding agents?
This somewhat widely cited post (I keep seeing it cited, anyway) suggests that dynamic languages and/or languages that represent things more concisely are more token efficient. It seems to be cited enough that LLM search results agree. For example, when I searched for "dynamic vs static language token cost" (no…
1087
AI can code, but it can't build software
AI can write code, but it can’t build real software. Software engineering remains human work because AI can code, not engineer.
1088
1089
Why host your own LLM?
In the Terminator movies, good relationships beat technological superiority. Kyle Reese and Sarah Connor outwit the advanced T-800 who in turn helps Sarah and John beat the ultra-advanced T-1000. OpenAI’s GPT-4 is currently the most advanced publicly available language model. There are also analyses showing it’s…
1090
Task Paralysis and AI
An article about ADHD, Task Paralysis and AI.
1091
Explainer: What's r1 and everything else?
Principal AI Architect. Creator of open-strix, a harness for building agent teams. Writing about AI architecture, stateful agents, and what happens when you give AI memory.
1092
1093
What a Deep Neural Network thinks about selfies
Musings of a Computer Scientist.
1094
1095
The state of AI for hand-drawn animation inbetweening
There are many potential ways to use AI 1 (and computers in general) for 2D animation. I’m currently interested in a seemingly conservative goal: to improve the productivity of a traditional hand-drawn full animation workflow by AI assuming responsibilities similar to those of a human assistant.
1096
The Einstein AI Model
I shared a controversial take the other day at an event and I decided to write it down in a longer format: I’m afraid AI won't give us a compressed 21st century.
1097
What sort of maths are LLMs good at?
For the sake of anyone who might read this blog post in the distant future (a month from now, say), let me mention that I am writing it a few days after OpenAI announced that it had solved ten majo…
1098
From Bing to Sydney
More on Bing, particularly the Sydney personality undergirding it: interacting with Sydney has made me completely rethink what conversational AI is important for.
1099
Short Message Compression Using LLMs
ts_sms works similarly to ts_zip . It uses a specific padding system compatible with arithmetic coding so that the message length does not need to be explicitly encoded.
1100
Using ChatGPT for home automation
In another thrilling adventure with ChatGPT, I endeavored to integrate it with a Raspberry Pi, effectively turning it into my own personal light switch. My custom ChatGPT plugin, sporting just two ...
1101
A common mistake when NumPy’s RNG with PyTorch
A bug that plagues thousands of open-source ML projects.
1102
LLM abstraction levels inspired by fish eye lens
We often think of the same information at different levels or abstraction. Here's a simple example:
1103
Autonomous trucking is harder than autonomous rideshare
Freeways were supposed to be easy. What happened?
1104
Norway should buy OpenAI
The Long Arc of History Bends Towards Social Democracy
1105
Humane AI – Pico Laser Projection – AI Twist on an Old Scam (2023)
Humane AI (Humane, hereafter) combines the mid-2010s failed concept of using a laser projector to project on the body with the early 2000s failed projector phone (something I wrote about in 2013), …
1106
1107
Gmail AI gets more intrusive
Gmail doesn't just offer to write your emails for you, they actually do it, and it's up to you to delete the text it wrote. Hard to make a screen shot to demo without revealing personal i…
1108
1109
David J.C. MacKay, Machine Learning pioneer, dies
Thank you so much to lots of lovely friends who have offered to visit me in hospital! Ramesh and I are wanting to keep life really simple...
1110