Tim Chambers
boosted
Want to really understand how RAG, vector search & chunking work?
Then stop reading theory and build your own chatbot.
This guide shows you how to create a local PDF chatbot using:
☕ LangChain
☕ FAISS (vector DB)
☕ Mistral via Ollama
☕ Python & Streamlit
Step-by-step, from environment setup to deployment. Ideal for learning how Retrieval-Augmented Generation works in practice.
Comment “WANT” if you need the friends link to the article, as you don’t have paid Medium.
#rag #tech #Technology #chatbot #AI #ki #python #vector #langchain #datascience #DataScientist #streamlit
Want to really understand how RAG, vector search & chunking work?
Then stop reading theory and build your own chatbot.
This guide shows you how to create a local PDF chatbot using:
☕ LangChain
☕ FAISS (vector DB)
☕ Mistral via Ollama
☕ Python & Streamlit
Step-by-step, from environment setup to deployment. Ideal for learning how Retrieval-Augmented Generation works in practice.
Comment “WANT” if you need the friends link to the article, as you don’t have paid Medium.
#rag #tech #Technology #chatbot #AI #ki #python #vector #langchain #datascience #DataScientist #streamlit
I knew AI would ruin interviews but this is way beyond my lowest expectations. So sad to finally bypass the ATS and getting a malfunctioning AI interviewing you.
…“It’s extraordinary,” said Simon Willison, an independent #AI researcher who’s been testing the tool. “You can ask it a sort of pointed question that is around controversial topics. And then you can watch it literally do a search on X for what #ElonMusk said about this, as part of its research into how it should reply.”
One example widely shared on social media — & which Willison duplicated — asked #Grok to comment on the conflict in the #MiddleEast. The prompted question made no mention of #Musk, but the #chatbot looked for his guidance anyway.
As a so-called reasoning model, much like those made by rivals #OpenAI or #Anthropic, #Grok4 shows its “thinking” as it goes through the steps of processing a question & coming up with an answer.
This was always going to happen, Linda Yaccarino was always essentially a lame-duck CEO for Musk.
https://mstdn.social/@stux/114823870299604008
@thisismissem
So
Jumped, or was pushed?
mhmm...
"New York CNN —
#LindaYaccarino is stepping down as CEO of #X after two years leading #ElonMusk’s social media company.
#Yaccarino’s departure comes one day after the company’s #Grok#Chatbot began pushing antisemitic tropes in responses to users. It’s not clear that the events were connected. "
Christine Lemmer-Webber 🌀
and 1 other
boosted
I mean seriously… what did they expect from an AI owned by a sig-heiling Nazi.
“The year is 2025, and an AI model belonging to the richest man in the world has turned into a neo-Nazi.”
For the media’s next trick they will be surprised when the new political party owned by a Nazi billionaire calls itself a “workers party” but hates communists and socialists alike.
Atlantic: https://www.theatlantic.com/technology/archive/2025/07/grok-anti-semitic-tweets/683463/
Archive link: https://archive.is/2025.07.09-012609/https://www.theatlantic.com/technology/archive/2025/07/grok-anti-semitic-tweets/683463/
#grok #musk#AI #chatbot #twitter#X
I mean seriously… what did they expect from an AI owned by a sig-heiling Nazi.
“The year is 2025, and an AI model belonging to the richest man in the world has turned into a neo-Nazi.”
For the media’s next trick they will be surprised when the new political party owned by a Nazi billionaire calls itself a “workers party” but hates communists and socialists alike.
Atlantic: https://www.theatlantic.com/technology/archive/2025/07/grok-anti-semitic-tweets/683463/
Archive link: https://archive.is/2025.07.09-012609/https://www.theatlantic.com/technology/archive/2025/07/grok-anti-semitic-tweets/683463/
#grok #musk#AI #chatbot #twitter#X
This is obviously bad from #whatsapp, but also, the way the journalist describes what the chatbot does, as if it had intentions, is pretty bad too.
"It was the beginning of a bizarre exchange of the kind more and more people are having with AI systems, in which chatbots try to negotiate their way out of trouble, deflect attention from their mistakes and contradict themselves, all in an attempt to continue to appear useful."
No, the chatbot isn't "trying to negotiate", and is not "attempting to appear useful". It's a program that follows programming rules to output something that looks like English langage. It doesn't have desires or intentions, and it cannot lie because it doesn't know what truth is.
‘It’s terrifying’: WhatsApp AI helper mistakenly shares user’s number
https://www.theguardian.com/technology/2025/jun/18/whatsapp-ai-helper-mistakenly-shares-users-number?CMP=Share_AndroidApp_Other