2941
Building a Multi-Agent System from Scratch: Architecture Patterns
Orchestrator-worker, blackboard, and pipeline patterns for coordinating multiple AI agents — with the failure modes that only show up once you go past a single-agent demo.
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 3,092 posts.
2942
Text Classification by Data Compression
Edit – I posted this on Hackernews and got some valuable feedback. Many brought up the fact that you should be able to reuse the internal state of the compressor instead of recompressing the training …
2943
Bayesian statistics and machine learning: How do they differ?
My colleagues and I are disagreeing on the differentiation between machine learning and Bayesian statistical approaches. I find them philosophically distinct, but there are some in our group who would like to lump them together as both examples of machine learning. I have been favoring a definition for Bayesian…
2944
2945
Gaussian explosion
Over the past month it seems like Gaussian Splatting (see my first post ) is experiencing a Cambrian Gaussian explosion of new research. The seminal paper came out in July 2023, and starting about mid-November, it feels like every day there’s a new paper or two coming out, related to Gaussian Splatting in some way…
2946
My Education in Machine Learning via Cousera, A Review So Far
As of today I’ve completed my fifth course at Coursera, all but one being directly related to Machine Learning. The fact that you can now take classes given by many of most well known researchers i…
2947
Narrative Jailbreaking for Fun and Profit
Posted on Monday 23 Dec 2024. 1,634 words, 1 link. By Matt Webb.
2948
2949
Gradient Boosting Explained in 3D
Understanding gradient boosting with interactive 3d-demonstrations
2950
Deep Learning on the GPU in Clojure from Scratch: Sharing Memory
Sharing and reusing memory buffers is inescapable if we want high performance. It is a sharp but powerful tool.
2951
Exploring Neural Graphics Primitives
Neural fields have quickly become an interesting and useful application of machine learning to computer graphics. The fundamental idea is quite straightforward: we can use neural models to represent all sorts of digital signals, including images, light fields, signed distance functions, and volumes.
2952
GSoC'24: Differentiable Logic for Interactive Systems and Generative Music
Last summer , I participated in Google Summer of Code for the first time, working with GRAME on improving support for using the Faust audio programming language on the web .
2953
2954
A Gentle Introduction to Markov Chain Monte Carlo (2012)
Applying probabilistic models to data usually involves integrating a complex, multi-dimensional probability distribution. For example, calculating the expectation/mean of a model distribution invol…
2955
Why are good developers so wary of agentic development?
Good developers’ caution about agentic development comes from knowing that built isn’t the same as working in production.
2956
Re: My AI skeptic friends are all nuts
Re: My AI Skeptic Friends Are All Nuts There was a post recently that was dissing AI Skeptics. While the post is funny at times, I feel like it’s absolutely and completely missing the point of the skepticism. Or at least I feel that it is glossing over some massive pain points of said skepticism. Let’s go over some of…
2957
AIs Will Increasingly Fake Alignment
This post goes over the important and excellent new paper from Anthropic and Redwood Research, with Ryan Greenblatt as lead author, Alignment Faking in Large Language Models.
2958
Codex vs. Claude Code (today)
Every AI tool has its strengths and weaknesses, and the only way to discover what they are is by using them.
2959
Where's the AI design Renaissance?
AI design is currently overhyped · Will AI take design jobs? · What should designers focus on in light of rapidly changing AI tools?
2960
Prompting LLMs is not engineering
prompt engineering is nothing but an attempt to reverse-engineer a non-deterministic black box for which any of the parameters below are unknown: - training set - weights - constraints on the model - layers between you and the model that transform both your input and the model's output that can change at any time …
2961
AI-Powered Meeting Scheduler X.ai Raises $9.2M Series A
I invest in early-stage AI, ML, and data startups at FirstMark Capital, and I write about the space here
2962
2963
2964
Using WolframAlpha to Hack Text CAPTCHA
I’ve been playing around with the Text CAPTCHA demo page and wondered how well WolframAlpha is at logic questions. As it turns out, Wolfram is pretty smart! Although, since a CAPTCHA requir…
2965
Robots Must Be Ephemeralized
There is a subfield of robotics research called “sim-to-real” (sim2real) whereby one attempts to solve a robotic task in simulation, and the...
2966
Making a vintage LLM from scratch
In this blog post, I will share the adventures I had creating my own LLM, from (almost) scratch, trained only on old texts. I made my own base-training and fine-tuning scripts, data processing pipelines and custom datasets. ("almost from scratch" means I did use existing programming languages and libraries, I didn't…
2967
Implementing the Goodfellow GANs paper
Generative Adversarial Networks (GANs), discovered by Ian Goodfellow in 2014, were an early method in the area of generative AI. I will focus on image generation as set out in the paper Generative Adversarial Nets 1 . This paper is the focal point of the post, I will guide you through the implementation of the paper…
2968
2969
Empirical Bayes for multiple sample sizes
The James-Stein Estimator with unequal variances
2970
Playing with genetic algorithms in Python
Edit: This post made it to the front page of Hacker News! You can find the discussion here.