Difference between revisions of "IT-AI-Base"

From wiki.samerhijazi.net
Jump to navigation Jump to search
(Buzz Words)
(Examples of LLMs)
Line 37: Line 37:
  
 
==Examples of LLMs==
 
==Examples of LLMs==
* GPT-4
+
* GPT-4 → chatgpt.com
* LLaMA
+
* LLaMA (https://www.llama.com/) from Meta
 
* Mistral
 
* Mistral
 
* Gemma
 
* Gemma
 +
* Claude → Claude.ai
 +
* Gemini → https://gemini.google.com/app
  
 
=Regulatory Requirements=
 
=Regulatory Requirements=
 
* Regulatory requirements (MaRisk, BAIT, DORA)
 
* Regulatory requirements (MaRisk, BAIT, DORA)
 
* BAIT, DORA oder ISO 27001.
 
* BAIT, DORA oder ISO 27001.

Revision as of 14:29, 8 April 2026

init

Buzz Words

  • LLM (Large Language Model)
  • LLMOps
  • Generative KI
  • RAG-Anwendungen
  • GenAI und Agentic AI Tools (z. B. LlamaIndex, LangChain/LangGraph).
  • LangGraph-orchestrated LLM agents to autonomously investigate cloud incidents
  • PagerDuty, Datadog, Grafana, Netdata, Dynatrace, Coroot, ThousandEyes, BigPanda
  • Any tool that can send webhooks can trigger an automated investigation.
  • How is Aurora different from Rootly or incident.io?

LLM

  • A Large Language Model (LLM) is an AI system trained on huge amounts of text to understand and generate human-like language.
  • An LLM is a program that predicts the next word in a sentence, based on everything it has learned from massive datasets.
  • LLM = very advanced autocomplete trained on the internet

What LLMs can do

  • Answer questions
  • Write emails, essays, code
  • Translate languages
  • Summarize documents
  • Chat like a human

What LLMs can't do

  • LLMs don’t “think” like humans.
  • Don’t truly understand meaning
  • Don’t have opinions
  • Just predict the most likely next words based on patterns

Examples of LLMs

Regulatory Requirements

  • Regulatory requirements (MaRisk, BAIT, DORA)
  • BAIT, DORA oder ISO 27001.