AI/LLM: Difference between revisions
< AI
Jump to navigation
Jump to search
(→Notes) |
|||
| Line 8: | Line 8: | ||
** '''2023-03-16''' [https://blog.kagi.com/kagi-ai-search Kagi's approach to AI in search] | ** '''2023-03-16''' [https://blog.kagi.com/kagi-ai-search Kagi's approach to AI in search] | ||
* [https://www.perplexity.ai/ Perplexity] | * [https://www.perplexity.ai/ Perplexity] | ||
** [https://www.perplexity.ai/search/what-software-is-needed-for-tr-XT_VpmS4RRiFBZF0bvuNOQ What software is needed for training a large language model (LLM)?] | |||
==Notes== | ==Notes== | ||
* '''2024-10-07''' [https://arxiv.org/pdf/2410.05229 GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models] (paper by Apple researchers; [https://sfba.social/@drahardja/113310311247575811 via]) | * '''2024-10-07''' [https://arxiv.org/pdf/2410.05229 GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models] (paper by Apple researchers; [https://sfba.social/@drahardja/113310311247575811 via]) | ||
Revision as of 12:20, 16 October 2024
|
Large Language Model AI (LLMs)
|
I often use these for answering questions (usually technical, occasionally political).
commercial services
- ChatGPT (by OpenAI, which is neither open nor AI[1])
- Copilot (Microsoft)
- FastGPT: seems to be Kagi's own model, not just a front-end to some other LLM
- Perplexity
Notes
- 2024-10-07 GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models (paper by Apple researchers; via)
- 2023-05-24 Worried About Sending Your Data to a Chatbot? 'PrivateGPT' Is Here
Code Sources
- Auto-GPT «chains together LLM "thoughts", to autonomously achieve whatever goal you set.»
- Downside: not fully autonomous; still depends on OpenAI
- privateGPT
Footnote
- ↑ ...in the sense that LLMs in general are not really what the term "AI" means to me.