Activity
Mon
Wed
Fri
Sun
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
What is this?
Less
More

Memberships

Data Alchemy

38k members • Free

8 contributions to Data Alchemy
(Rant) What will tariffs mean for AI in your country?
Do you think the upcoming tariffs and the potential subsequent protectionist world order will result in all countries developing their own AI/AGI, and end reliance on LLMs from OpenAI etc? What would different societies look like when they shut their borders, develop their own AGI and robotics, making work essentially a thing of the past for most? Would some more socialist inclined countries have these resources tend for their citizens creating a "utopia"? And would countries with a more capitalist mindset let these resources be concentrated to the superwealthy that owns this technology, and at the same time as the human workforce becomes progressively more and more obsolete, they get thrown out on the streets, with no way to lift themselves out of the misery as the AI that is owned by the elite does everything better, and there is no alternative way of making money? What would YOUR country look like you think?
RAG in Short
I believe most of you know what RAG is. But some might not. I am personally very exited on the LLM development possibility of Graph RAG. So let me share what in short RAG is as a foundation. Retrieval-Augmented Generation (RAG) is a popular method in AI that solves the problem of language models forgetting or not knowing specific or updated information, especially in real-world or specialized use cases. While traditional in-context learning only uses the few examples or prompts provided at the time of the query, RAG goes a step further by actively searching a connected knowledge base—like a set of documents or a company’s database—for relevant information, then feeding those results into the language model to generate more accurate and grounded answers. This makes RAG especially useful when you need reliable, source-based responses. To implement it, you store your data in a searchable format (usually in a vector database), use an embedding model to match user questions with the most relevant chunks of information, and then give both the question and retrieved content to the language model to generate a smart, well-informed response. See this information: https://www.youtube.com/watch?v=T-D1OfcDW1M&t=18s
1 like • Apr 7
More reliable and transparent info, less hallucinations, and (when info changes) editable information since you can clearly track the answers. Should be the standard imo.
Awesome Foundation Agents
"We maintain a curated collection of papers exploring the path towards Foundation Agents, with a focus on formulating the core concepts and navigating the research landscape." https://github.com/FoundationAgents/awesome-foundation-agents
0 likes • Apr 7
Thanks for the link. I read the abstract of this 250+ pages paper, and it seems like an interesting theoretical read. Has anyone read the whole thing? Does it have any practical use for the common Joe here aiming at developing their own AI agents?
1 like • Apr 6
All these cautionary tales just speaks to the importance of as many as possible REALLY learning AI, so even if we who have gathered here are potentially pushing our own demise by promoting AI development, we are also democratizing this knowledge, which should hopefully to some extent limit any powerhouse from getting the upper hand and abuse that power in an anti-human way.
1 like • Apr 7
@Pierre-Henry Isidor My point didn't come across very well, so I'll try to rephrase my comment. My point was that EVEN IF we were to push our own demise by working with AI, the genie is already out of the bottle and the evolution of AI is inevitable with or without our contribution. So what we are doing, learning and sharing, is essentially democratizing this knowledge, which should hopefully to some extent limit any powerhouse from getting the upper hand and abuse that power in an anti-human way. So, looking into my own intentions, I am driven by my own curiosity, a hope that AI might be able to contribute to better healthcare (which is my field), and a conviction that this knowledge should be in the hands of the many.
Classroom>Alchemy Codex>Chapter 1>Code Editor Configuration > Missing document?
Hi all! So I´m following along the videos in the classroom, and I have reached the "Code Editor Configuration"-video (ie where you set up VS Code) in Alchemy Codex>Chapter 1. Dave is referring to a document during this video, which judging from the pattern from previous videos/lessons should be available under the video, in the description part on the very same page as the video. This is not the case here, and this makes it a bit difficult to follow. Has it perchance been removed by mistake, or is the document available somewhere else to better follow along this video?
1-8 of 8
Daniel Fonte
3
15points to level up
@daniel-fonte-3845
Now a M.D., but 10 years ago I was a programmer who dabbled in AI, an interest reignited by recent advancements of AI and the possible medical uses.

Active 222d ago
Joined Feb 4, 2025
Powered by