ChatGPT cheat sheet
#ChatGPT #chatgpt4 #AI #cheatsheets #OpenAI #ArtificialIntelligence #IoT #javascript #programming #coding #technology
LLMS
-
ChatGPT Cheat Sheet for Developers and AI Enthusiasts
By
–
-
Correction: ChatGPT uses GPT-3.5, requesting GPT-4 comparisons
By
–
whoops misrepresented this… ChatGPT in this case is actually 3.5 GPT-4 is still an early version of the model, however, would like to see the comparisons redone with the GPT-4 in ChatGPT
-
LLM Agents: From NPCs to General Task Execution
By
–
We started working on LLM-driven agents a year ago. The first use case was a rewrite of NPCs for our AI Game; the second was general agents that can execute tasks, learn from feedback, use tools, etc. In retrospect, we should have been more aggressive in the second use case.
-
LLMs for NPC Behavior Control in Games Beyond Conversation
By
–
Interestingly, when people discuss LLMs and game NPCs, they mostly see only the conversational AI use case. But there is another option: using LLMs to control NPC's behavior. This would let NPCs interact with the game world (observe and act) and even talk to other NPCs,
-
AI Capabilities Limited by Human-Generated Data Dependencies
By
–
a superpowerful AI that surpasses all humanity is far fetched based on today’s tech all of their capabilities and talents have been gifted to them by human-generated data (internet + RLHF) these models, while insane learners, do not self improve it is impressive, but not magic
-
Paper Recommendations: RLHF Model Outputs and Comparisons
By
–
highly recommend taking a quick scan of the paper, you would love it they show some great comparisons between the base model outputs and the RHLF outputs – from generating Shakespeare to demonstrating visual imagination here are some examples just from the first 10 pages:
-
GPT-4 Response Complexity Limited Despite Jailbreak Attempts
By
–
yeah I agree even with the jailbreaks, the level of complexity in GPT's responses is severely lacking compared to what I imagine the base model would generate (extrapolating from the system card outputs) based on the GPT-4 paper's benchmarks and these sorts of responses, the
-
LAION_AI Calls for Supercomputer to Develop Open-Source AI Models
By
–
Truly Open AI. @LAION_AI calls for a supercomputer to develop open-source AI, by replicating large models like GPT-4 and exploring them together as a research community.
-
AutoGPT Viruses: Security Risk and Single Point of Failure
By
–
Could we soon see AutoGPT viruses spreading from computer to computer? While this scenario may sound like science fiction, the possibility exists. However, these viruses would have a single point of failure (LLM provider API), which means they could be shut down relatively
-
W23 Startups Leverage Generative AI Chatbots for Enterprise Sales Support
By
–
CBI: “Several W23 startups allow companies to leverage generative AI chatbots to support sales (e.g., Lightski) and customer support (e.g., Kyber) teams. Others provide tools for enterprise developers to build their own large language model (LLM) applications (e.g., Stack AI).”