When a chatbot runs your store

When a chatbot runs your store

⋅

You may have heard of people hooking up chatbots to controls that do real things. The controls might run internet searches, run commands to open and read documents and spreadsheets, or even edit or delete entire databases. Whether this sounds like a good idea depends in part on how bad it is if the chatbot does something destructive, and how destructive you’ve allowed it to be. That’s why running a single in-house company store is a good test […]

Ver mais

Liked Liked

Missed Shiba Inu and PEPE? Pepeto Offers a Second Chance at Early Gains

⋅

Shiba Inu has generated about 150,000X returns since its launch in August 2020 and PEPE has paid out more than 46,000X to first entrants since April 2023. Both the tokens presently trade at multi-billion dollars valuations that deny them any similar percentage gains to the present value. SHIB has a market cap of over $5B, and PEPE has approximately $2.7B which puts them in mathematical limits regarding the possibility of massive future growth. Cryptocurrency whale wallets have distinctive […]

Ver mais

Liked Liked
“Dr AI, am I healthy?” 59% of Brits rely on AI for self-diagnosis

“Dr AI, am I healthy?” 59% of Brits rely on AI for self-diagnosis

⋅

AI advancements are changing the way we look at health and deal with health-related issues. According to a new nationwide study by Confused.com Life Insurance, three in five Brits now use AI to self-diagnose health conditions. Through various searches, like side effects of medical conditions, treatment options, and symptom checks, as much as 11% of respondents claim AI has helped improve their conditions. More than a third (35%) are likely to use AI in this context in the […]

Ver mais

Liked Liked
Is This a Paper Review?

Is This a Paper Review?

⋅

With paper submissions rocketing and the pool of experienced researchers stagnant, machine learning conferences, backs to the wall, have made the inevitable choice to inflate the ranks of peer reviewers, in the hopes that a fortified pool might handle the onslaught. Infographic depicting NIPS submissions over time. The red bar plots fabricated data from the future. With nearly every professor and senior grad student already reviewing at capacity, conference organizers have gotten creative, finding reviewers in unlikely places. […]

Ver mais

Liked Liked

Unit-Consistent (UC) Adjoint for GSD and Backprop in Deep Learning Applications

⋅

Deep neural networks constructed from linear maps and positively homogeneous nonlinearities (e.g., ReLU) possess a fundamental gauge symmetry: the network function is invariant to node-wise diagonal rescalings. However, standard gradient descent is not equivariant to this symmetry, causing optimization trajectories to depend heavily on arbitrary parameterizations. Prior work has proposed rescaling-invariant optimization schemes for positively homogeneous networks (e.g., path-based or path-space updates). Our contribution is complementary: we formulate the invariance requirement at the level of the backward adjoint/optimization […]

Ver mais

Liked Liked
Google announces AI Overviews in Gmail search, experimental AI-organized inbox

Google announces AI Overviews in Gmail search, experimental AI-organized inbox

⋅

Gmail made us all rethink how email could work when it debuted more than 20 years ago. Google thinks we’re in the process of another email transformation courtesy of AI. The company has unveiled a new round of AI features that will make Gemini an even more integral part of Gmail. The new Gemini experiences are coming to paying subscribers starting today, and a collection of previously premium-only AI features are rolling out widely. AI Overviews first appeared […]

Ver mais

Liked Liked

About Feature Scaling and Normalization

⋅

I received a couple of questions in response to my previous article (Entry point: Data) where people asked me why I used Z-score standardization as feature scaling method prior to the PCA. I added additional information to the original article, however, I thought that it might be worthwhile to write a few more lines about this important topic in a separate article.

Ver mais

Liked Liked

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models

⋅

arXiv:2601.05445v1 Announce Type: new Abstract: Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain a coherent progression over long interactions, often losing track of what has been accomplished and what remains to be done; they rely on rigid or pre-defined patterns, and fail to adapt to the LLM’s dynamic […]

Ver mais

Liked Liked

This 30-Year-Old Entrepreneur Wants To Build Southeast Asia’s Answer To Hims & Hers

⋅

A 30-year-old Danish entrepreneur is building Southeast Asia’s answer to Hims & Hers. Launched in the Philippines, &you offers private online doctor consultations and discreet medication delivery. By focusing on speed, privacy, and cultural trust, the startup aims to fix healthcare access gaps and reach unicorn status within three years.

Ver mais

Liked Liked
Build Advanced RAG with LangGraph

Build Advanced RAG with LangGraph

⋅

image by author Bringing together Self-reflection, Corrective, and Adaptive systems We all know and love Retrieval-Augmented Generation (RAG). The simplest implementation of Retrieval-Augmented Generation (RAG) is a vector store with documents connected to a Large Language Model to generate a response from a query. This is known as a Single Step Approach. For simple queries this strategy is quite effective, especially if the documents have the answer the user is looking for. However, LangGraph introduced architecture that can enhance the RAG […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025