A computer agent that can understand natural language and perform tasks on a computer. They used a large pre-trained language model and a simple prompting scheme that helps the agent improve its output. https://arxiv.org/abs/2303.17491
LLMS
-
LLaMA-Adapter: Efficient Fine-tuning with Zero-init Attention
By
–
5. LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention LLaMA-Adapter is a fast way to improve an model's ability to follow instructions, producing quality responses and working with images for better problem-solving. https://
arxiv.org/abs/2303.16199 -
BloombergGPT: Large Language Model for Finance
By
–
1. BloombergGPT: A Large Language Model for Finance BloombergGPT is a language model trained on a large financial dataset that outperforms other models on financial tasks https://
arxiv.org/abs/2303.17564 -
Comprehensive Survey of Large Language Models: Techniques and Resources
By
–
A Survey of Large Language Models/LLMs LLMs are one of the hot things nowadays. This review paper provides a comprehensive overview of recent advances in LLMs(background & mainstream techniques). Also covers resources for developing/building with LLMs. https://
arxiv.org/abs/2303.18223 -
Migration vers GPT-4 : adoption et utilisation actuelle
By
–
chez nous on est encore a fond je pense, et ils faut voir si ils ont pas migré vers la requête gpt4 aussi
-
Sam Bowman’s Survey: Essential Reading for LLM Researchers
By
–
This survey from Sam Bowman is worth reading, even for LLM researchers – it helped organize my thinking around the implications in the recent literature (including unspoken/implicit implications!)
-
GPT-4 is Much Harder to Jailbreak Than Previous Models
By
–
coming from someone who has jailbroke gpt-4 a few times now and posted about it on here, it is much much harder to jailbreak than prior models it also appears they have also done some pretty heavy work on their new chatML system and it is working very well across models
-
How Large Language Models Work for Enterprise
By
–
Generative #AI has stunned the world with its ability to create realistic images, code, and dialogue.
— IBM Data, AI & Automation (@IBMData) 3 avril 2023
📹 In this video, IBM expert Kate Soule explains how a popular form of generative AI, large language models, works and what it can do for enterprise: https://t.co/jsuQzfrDVV pic.twitter.com/VXZoBA4HJAGenerative #AI has stunned the world with its ability to create realistic images, code, and dialogue. In this video, IBM expert Kate Soule explains how a popular form of generative AI, large language models, works and what it can do for enterprise: https://
ibm.co/3zqWaHm -
LLMs as Natural Language Computers: Programming Through Clear Communication
By
–
LLMs are natural language computers – trained by natural language, programmable by natural language. The best way to program LLMs may simply be to communicate clearly and precisely.
-
Confidence in LLM Development and Future Perspectives
By
–
Not exactly, there are and will be others who fab LLMs. But I have increasing confidence in the last paragraph of this post https://
karpathy.github.io/2022/03/14/lec
un1989/
…