Will AutoGPT-style AI Agents mostly work before the end of 2024?
60
1kṀ2959Dec 27
17%
chance
1H
6H
1D
1W
1M
ALL
Right now, AutoGPT and BabyAGI don't really work. If you give them a complex task they go off the rails and get stuck in loops, so most people prefer to use the models directly rather than an agent scaffold.
Will there be advancements in scaffolding this year or new models such as GPT-5 that solve these problems and allow them to mostly work? I will try the agents myself, and factor in whether it is common for people to use LLM agent frameworks for productivity assistant tasks.
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000People are also trading
Related questions
Will there be an AI language model that strongly surpasses ChatGPT and other OpenAI models before the end of 2025?
44% chance
Will a smart agent pass our Turing test by the end of 2025?
56% chance
Will an AI system beat humans in the GAIA benchmark before the end of 2025?
68% chance
AutoGPT style agents will prove in the longer run the proper way to get automation of medium complexity tasks.
27% chance
Will GPT, or AI systems that have GPT as their main component, become as reliably factual as Wikipedia, before 2026?
49% chance
Will an AI system similar to Auto-GPT make a successful attempt to kill a human by 2030?
24% chance
Will Meta AI start an AGI alignment team before 2026?
45% chance
At the start of 2030 will I believe that OpenAI had AGI in 2024?
10% chance
Will an AI run a factory by the end of 2028 (start of 2029)
14% chance
Will OpenAI be in the lead in the AGI race end of 2026?
40% chance