GenAI

GenAI

694 bookmarks
Newest
A Visual Guide to LLM Agents
A Visual Guide to LLM Agents
Explore the main components of what makes LLM Agents special.
An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators.
Agents interact with their environment and typically consist of several important components
chain-of-thought
This is where planning comes in. Planning in LLM Agents involves breaking a given task up into actionable steps.
reasoning” and “thinking” a bit loosely as we can argue whether this is human-like thinking or merely breaking the answer down to structured steps.
without any examples (zero-shot prompting)
Providing examples (also called few-shot prompting7)
ReAct
Reflecting
These Multi-Agent systems usually consist of specialized Agents, each equipped with their own toolset and overseen by a supervisor.
three LLM roles
SELF-REFINE
To enable planning in LLM Agents, let’s first look at the foundation of this technique, namely reasoning.
ConceptConcept#learning-list
·newsletter.maartengrootendorst.com·
A Visual Guide to LLM Agents
Do you know the answer to these three questions? You should... 1. What are vector embeddings and embedding models? 2. What’s the benefit of having a vector database for vector search? 3. What’s on the next horizon for AI applications? I just finished a 3-part webinar series… pic.twitter.com/nFOAPHQw2q— Victoria Slocum (@victorialslocum) March 5, 2025
Do you know the answer to these three questions? You should... 1. What are vector embeddings and embedding models? 2. What’s the benefit of having a vector database for vector search? 3. What’s on the next horizon for AI applications? I just finished a 3-part webinar series… pic.twitter.com/nFOAPHQw2q— Victoria Slocum (@victorialslocum) March 5, 2025
ConceptConcept#embedding#semantic-search#vector-similarity
·x.com·
Do you know the answer to these three questions? You should... 1. What are vector embeddings and embedding models? 2. What’s the benefit of having a vector database for vector search? 3. What’s on the next horizon for AI applications? I just finished a 3-part webinar series… pic.twitter.com/nFOAPHQw2q— Victoria Slocum (@victorialslocum) March 5, 2025
How to Hack AI Agents and Applications
How to Hack AI Agents and Applications
Learn how to hack AI agents and applications with this expert guide. Find vulnerabilities, prompt injection risks, and testing strategies for AI security.
SecuritySecurity
·josephthacker.com·
How to Hack AI Agents and Applications
AI-Tools
AI-Tools
Many students and researchers are already using them - tools with integrated artificial intelligence (AI). What can AI-supported tools achieve, what opportunities do they offer and what are their limitations? The following list is an introductory selection which is not based on any value judgement.
ToolsTools#academic#research
·ub.fau.de·
AI-Tools
"regular people don't fine-tune VLMs"
"regular people don't fine-tune VLMs"
but wtf not? - skill gap - high fine-tuning costs - lack of standards and unified approaches over the past few weeks I've been working on maestro - streamlined tool for VLM fine-tuning link: — SkalskiP (@skalskip92)
VLMVLM
·x.com·
"regular people don't fine-tune VLMs"
Open source: it works!
Open source: it works!
Two months ago user durable-racoon posted about DocumentContextExtractor, their iteration on a technique for improving the accuracy of RAG that both and had made demo implementations of. Contextual Retrieval improves the… — LlamaIndex 🦙 (@llama_index)
ConceptConcept#llamaindex#semantic-search
·x.com·
Open source: it works!
tjmlabs/ColiVara: Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.
tjmlabs/ColiVara: Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.
Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual...
Similar SolutionsSimilar Solutions#document-understanding#semantic-search#vector-similarity
·github.com·
tjmlabs/ColiVara: Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.