211
Web scraping with GPT-4o: powerful but expensive
tl;dr; show me the demo and source code!
New
The latest blog posts to take off on Hacker News. 673 posts.
212
AI-Implanted False Memories
We present three interconnected studies examining how artificial intelligence technologies can induce and amplify false memories in human subjects. Our re…
213
Building LLMs from the Ground Up: A 3-Hour Coding Workshop
If your weekend plans include catching up on AI developments and understanding Large Language Models (LLMs), I've prepared a 1-hour presentation on the development cycle of LLMs, covering everything from architectural implementation to the finetuning stages.
214
Update on Llama adoption
Llama models are approaching 350 million downloads to date, and they were downloaded more than 20 million times in the last month alone, making Llama the leading open source model family.
215
OpenAI is good at unminifying code
I was curious about how a component was implemented in a minified JavaScript file and used ChatGPT to reverse engineer the component.
216
Micrograd.jl
A series on automatic differentiation in Julia. Part 1 provides an overview and defines explicit chain rules.
217
Cerebras Inference: AI at Instant Speed
We are excited to announce the release of Cerebras DocChat, our first iteration of models designed for document-based conversational question answering. This series includes two models: Cerebras Llama3-DocChat, a large language model (LLM), and Cerebras Dragon-DocChat, a multi-turn retriever model.
218
219
220
Anthropic Claude 3.5 can create icalendar files, so I did this
Generate calendar entries from an image using Anthropic Claude 3.5. Convert lesson dates in an image to a calendar ICS file
221
Looming Liability Machines (LLMs)
As part of our zoom reading group ( wow, 4.5 years old now ), we discussed a paper that uses LLMs for automatic root cause analysis (RCA) fo...
222
Leveraging AI for efficient incident response
We’re sharing how we streamline system reliability investigations using a new AI-assisted root cause analysis system. The system uses a combination of heuristic-based retrieval and large language m…
223
Claude's API now supports CORS requests, enabling client-side applications
Anthropic have enabled CORS support for their JSON APIs, which means it’s now possible to call the Claude LLMs directly from a user’s browser. This massively significant new feature is …
224
What's Going on in Machine Learning? Some Minimal Models
Stephen Wolfram explores minimal models and their visualizations, aiming to explain the underneath functionality of neural nets and ultimately machine learning.
225
LM Studio 0.3 – Discover, download, and run local LLMs
LM Studio 0.3.0 is here! Built-in (naïve) RAG, light theme, internationalization, Structured Outputs API, Serve on the network, and more.
226
I'm tired of fixing customers' AI generated code
(Not an anti-AI post — Copilot is great, I use it all the time.)
227
228
Zed AI
From the Zed Blog: Powerful AI-assisted coding powered by Anthropic's Claude, now available.
229
Data Exfiltration from Slack AI via indirect prompt injection
Authors: PromptArmor
230
Fine-tuning now available for GPT-4o
Fine-tune custom versions of GPT‑4o to increase performance and accuracy for your applications.
231
AI companies are pivoting from creating gods to building products
Turning models into products runs into five challenges
232
233
LLMs know more than what they say
... and how that provides winning evals
234
235
Markov chains are funnier than LLMs
Predictability machines and personality
236
Are you better than a language model at predicting the next word?
A quiz to see how you compare to language models.
237
How to get from high school math to cutting-edge ML/AI
1) Foundational math. 2) Classical machine learning. 3) Deep learning. 4) Cutting-edge machine learning.
238
The future of Deep Learning frameworks
Assumed audience: ML researchers who frequently work with PyTorch , but are interested in trying out JAX or have yet to be convinced.
239
240