TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Autogen: Enable next-gen large language model applications

163 点作者 infruset超过 1 年前

14 条评论

anais9超过 1 年前
Have been working with this and very impressed so far - it’s a step ahead of LangChain agents and seems to be receiving more attention&#x2F;development than LangChain was interested in committing to agents.<p>FWIW the “group research” and “chess” examples from the notebooks folder in their repo have been the best for explaining the utility of this tech to others - the meme generator does a good job showing functions stripped down but misses a lot of the important bits
评论 #37933937 未加载
ugh123超过 1 年前
Matthew Berman has a good series on AutoGen with tutorials and demos: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=10FCv-gCKug">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=10FCv-gCKug</a><p>However from his examples (and his own admission) it seems that AutoGen isn&#x27;t benefitting from full GPT4-level performance even tho he&#x27;s pointed it directly at OpenAPI GPT4 (and other LLMs). The back and forth between the agents does not produce great results even tho similar prompts pumped directly into ChatGPT seem to give better results.<p>Anyone know whats going on?
评论 #37931886 未加载
TaylorAlexander超过 1 年前
This just reminds me: I have been wondering, if you get multiple instances of GPT-4 talking to each other, each seeded with a different personality prompt, do they have interesting conversations? I suspect it would devolve in to nonsense quickly, but I’ve never seen any chat log of two GPT instances talking. Does anyone have a reference for this? Thanks.
评论 #37935297 未加载
评论 #37935743 未加载
评论 #38029490 未加载
评论 #37933782 未加载
gavi超过 1 年前
Anyone trying this - Please note the python package is called pyautogen
h4kor超过 1 年前
A question for people researching LLMs and their capabilities:<p>Is there any reason to believe that the interaction of multiple agents (using the same model) will yield some emergent property that is beyond the capabilities of the agent model?<p>I&#x27;m not working with LLMs, but my intuition is that whatever these multi agent setups come up with could also be achieved by a single agent just talking to itself, as they all are &quot;just guessing&quot; what the most probable next token is.
评论 #37928422 未加载
评论 #37931666 未加载
评论 #37928814 未加载
评论 #37931585 未加载
评论 #37934681 未加载
评论 #37928503 未加载
评论 #37931794 未加载
评论 #37931537 未加载
评论 #37929080 未加载
评论 #37933672 未加载
评论 #37928918 未加载
ravix超过 1 年前
The breakthrough I&#x27;ve had is realizing how important it is to control the conversation between agents.<p>Just like in our work environments and in our relationships, HOW conversations occur largely determines the impact of the conversation. With or without AutoGen<p>We&#x27;re building a multi-agent postgres data analytics tool. If you&#x27;re building agentic software, join the conversation: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;4o8tymMQ5GM" rel="nofollow noreferrer">https:&#x2F;&#x2F;youtu.be&#x2F;4o8tymMQ5GM</a>
SunghoYahng超过 1 年前
Unless I&#x27;m missing something, how is this library different from prompting a single chatbot: &quot;Write a dialog in which A, B, and C, each playing a different role, have a conversation and do something D&quot;?
评论 #37933645 未加载
评论 #37930178 未加载
m3kw9超过 1 年前
Having conversations amongst agents is it like treating each agent as your traditional nodes? Maybe in the future there would be millions of nodes(agents) conversing and maybe this is how next gen AGI will form
评论 #37934327 未加载
评论 #37929657 未加载
dang超过 1 年前
A bunch of single-comment related threads. Others?<p><i>AutoGen: A Multi-Agent Framework for Streamlining Task Customization</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37855314">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37855314</a> - Oct 2023 (1 comment)<p><i>Microsoft&#x27;s AutoGen – Guide to code execution by LLMs</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37822809">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37822809</a> - Oct 2023 (1 comment)<p><i>Making memes with Autogen AI (open source LLM agent framework) [video]</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37750897">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37750897</a> - Oct 2023 (1 comment)<p><i>AutoGen: Enabling next-generation large language model applications</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37647404">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37647404</a> - Sept 2023 (1 comment)<p><i>AutoGen: Enabling Next-Gen GPT-X Applications</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37220686">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=37220686</a> - Aug 2023 (1 comment)
MawKKe超过 1 年前
Is Microsoft chronically incapable of coming up with original names?
评论 #37928637 未加载
digitcatphd超过 1 年前
It doesn’t help you inherently solve the problem per se, but what it does allow you to do that is distinctive is keep the human and the loop that can assist the agents to solve problems. To some degree it can also keep problems in the logic chain from snowballing, and causing the overall objective to fail because there’s invalid logic in the sequence
a_bonobo超过 1 年前
Are these &#x27;safer&#x27; than using langchain-based agents that directly execute (arbitrary!) Python code? That was always my main issue with langchain
评论 #37928996 未加载
评论 #37934351 未加载
zerop超过 1 年前
Use cases for multi agents?
评论 #37933804 未加载
webappguy超过 1 年前
AutoGen is great, but have you heard of GeniA?