multi-modal models like GPT-4 will significantly expand current capabilities beyond what's possible in a text-only model here are a few examples of some of the things these models can do (from the MM-ReAct paper) image hooking up one of these models to a pair of AR glasses…
LLMS
-
GPT-4 Potential: Prompt Design and Meta-Cognition Strategies
By
–
Good example of us not seeing max GPT-4 capability yet, imo. Prompt design, tool use, meta cognition strategies (eg idea of attempt, critique, retry, capabilities model, etc) are very likely to go a long way.
-
ChatGPT generates Python code with LangChain Pinecone integration
By
–
Not yet. Having ChatGPT write Python code by feeding it documentation from Langchain pinecone openai, etc
-
Analysis of the impact of AI and GPT4 on employment
By
–
Will #AI and #GPT4 destroy YOUR JOB? Full analysis → https://youtu.be/YZEzAuLNsQE You will see: yes, some jobs will disappear but others will appear (at least 10) #ArtificialIntelligence #AI #ChatGPT #ChatGPT4 #ChatGPTPlus
-
ChatGPT-4 integration in Skype preview
By
–
Did you know that you can chat with #chatgpt4 powered @bing inside the @Skype preview now?
-
LaMDA 2 deployment delayed, Bard appears outdated technology
By
–
pehaps they wait to deploy the real Lamda2 because bard seems to be more an old tech demo 🙂
-
LinkedIn Shows Dunning-Kruger Effect with AI ChatGPT
By
–
Looking at LinkedIn we are seeing an amazing example of the Dunning-Kruger effect #artificialintelligence #chatgpt
-
LLM hallucinations and search engine integration strategies
By
–
j'ai fait une conf la semaine dernière ou je parle de ça, les hallucinations, et d'ailleurs les intégrations "moteurs de recherche" vont tendre vers ça :" je cherche l'info d'abord ou tu passes au raisonnement LLM ?" https://
seosquare.semji.com -
Specialized AI Tools: Choosing Right Solver for Mathematical Problems
By
–
avec un doigt on peut planter des clous, mais si un marteau est plus adapté, on ira plutôt utiliser cet outil. Pareil pour les maths, y'a des solvers entrainés exactement pour ça.
-
We Got 32000 Tokens Instead of Flying Cars
By
–
we though we wanted flying cars and not 140/280 characters, but really we wanted 32000 tokens