361
Why AutoGPT engineers ditched vector databases
AutoGPT decided to drop the support for vector databases: Pinecone, Milvus, Redis, Weaviate - all gone. What has happened to the original idea of efficiently storing agent's memories?
362
363
LLM discourse needs more nuance
With this write-up, I want to outline my current thinking around large language models like OpenAI's chatGPT.
364
Why are there no antitrust claims vs. GitHub Copilot, when there is a precedent?
Microsoft GitHub released CoPilot last year, a tool for generating code and auto-completion, that’s been trained on vast amount of open source code, notably all open source code hosted on Git…
365
ChatGPT is really good at roleplaying
ChatGPT is really good at roleplaying as strange and unusual characters with minimal prompting.
366
The A.I. business influencer guys must be stopped
Please let's stop predicting the future of A.I.
367
The idea maze for AI startups (2015)
programming, philosophy, history, internet, startups
368
Changing my relationship with GitHub Copilot
I've been using GitHub Copilot on personal projects since March. It's been an interesting experience, and one that I realized I have to change. Using Copilot nearly full time has had some positive and negative impacts on me, and it's time to take control of how I interact with it.
369
Q* Hypothesis: Enhancing Reasoning, Rewards, and Synthetic Data
Emergency special: The information we need to understand what Q* is was right in front of us, but the memes are more fun than reality.
370
371
"Building Machines That Learn and Think Like People", 7 Years Later
In the post about GPT-4V, I mentioned the paper “Building Machines That Learn and Think Like People” (https://arxiv.org/abs/1604.00289) by Brenden Lake, Tomer Ullman, Joshua Tenenbaum, and Samuel Gershman.
372
ProfileGPT: An Example of AI Agents Collaboration Architecture
A dive into the architecture and design of ProfileGPT, an app that allows users to analyze their user's profile and personality as seen by ChatGPT to raise awareness about data usage.
373
Nvidia's CUDA Monopoly
CUDA (Compute Unified Device Architecture) is a closed-source low-level API that interfaces software with NVIDIA GPUs.
374
The Neural Net Tank Urban Legend
AI folklore tells a story about a neural network trained to detect tanks which instead learned to detect time of day; investigating, this probably never happened.
375
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…
376
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…
377
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.
378
379
ChatGPT is laying you off
(In various voices)
380
Playing with genetic algorithms in Python
Edit: This post made it to the front page of Hacker News! You can find the discussion here.
381
Bootstrapping self awareness in GPT-4: Towards recursive self inquiry
Or, Look Ma – I Made GPT-4 Self Aware!
382
OpenAI Begins Tackling ChatGPT Data Leak Vulnerability
OpenAI seems to have implemented some mitigation steps for a well-known data exfiltration vulnerability in ChatGPT. Attackers can use image markdown rendering …
383
384
Building a ChatGPT-enhanced Python REPL
In this blog I share my experience in building a Python REPL augmented with ChatGPT. I explore how the application is built, and speculate on software engineering patterns and paradigms that might emerge in systems built on Large Language Models (LLMs). GEPL - Generate, Evaluate, Print, Loop Link to this section…
385
Combine GPTs with private knowledge for actually useful AIs
Custom GPTs by OpenAI are practically free new hires. But as as new hires go, most are not very useful.
386
We're not Platonists, we've just learned the bitter lesson
Machine Alignment Monday, 7/24/23
387
388
A Multi-Level View of LLM Intentionality
Prompted by Keith Frankish's recent streamed discussion of LLM intentionality on YouTube , there's a particular idea I wanted to share which...
389
AI has poisoned its own well
What will happen to GPT-{n} once LLMs contribute much of the language found online? We find that use of model-generated content in training causes irreversible defects in the resulting models, where tails of the original content distribution disappear. We refer to this effect as Model Collapse and show that it can…
390
LLM Falcon 180B Needs 720GB RAM to Run
Yes, if you have enough CPU RAM