Has anyone actually done anything of use with autogpt? I tied it for 4 tasks and it would inevitably get stuck on each and produce absolutely nothing of value.
These were fairly simple like research popular topics and write articles on them etc.<p>It would do things like Google something, the result wasn’t relevant , try again , got an error from one of the pages and then seemingly started to do something completely incoherent related to the error message
To all the AI hucksters - there was a decades long effort already tried, known as "5th generation programming languages" where they assumed the next level after high level programming languages would be to remove the human programmer completely.<p>basically, this effort ended up failing because, well, problem solving itself is inherently complex.<p><a href="https://en.wikipedia.org/wiki/Fifth-generation_programming_language" rel="nofollow">https://en.wikipedia.org/wiki/Fifth-generation_programming_l...</a><p>seems like the exact same thing happened with ChatGPT / AutoGPT / GPT4, and this will keep happening.
I have never built an agent before, nor am I knowledgeable about the latest studies in this field. So what I am saying below is likely to be nonsensical.<p>I was thinking that perhaps we have been working with abstractions that are too low-level. Instead of providing a set of tools such as API calls or text splitters, wouldn't it be more reliable to give agents templates or workflows of successful tasks, such as trimming videos or booking restaurants?<p>These templates would consist of a set of function calls, or a graph of connected components in low-code tools like LangFlow. I believe auto agents already use a similar concept where they cache successful tasks for future reuse. The idea is to populate these caches with the most common use cases, and use retrieval if they become too large, so that we don't experience cache-miss most of the time and work with lower-level abstractions (tools) as the baseline. Templates, like prompts, should be portable (e.g. JSON) to avoid the need for everyone to reinvent the wheel. While this solution may not be as impressive as a full autonomous agent and may not work for a generalized case, it should produce a more predictable outcome, I think.
I know a big part of the discussion around this link is around whether AutoGPT is viable or not, but I think a more interesting piece are the papers linked at the bottom (especially the "Tool Maker" one). This pattern of "well, maybe the LLM can do that too" is just so obvious but so meta and simultaneously brittle. "LLM can use tools" -> "The tools can, themselves, be LLM-based" -> "The LLM can create it's own tools that it then uses".<p>It's really turtles all the way down.
The amount of hype around AutoGPT is probably good for other people building similar things though. It allows people to build without all the grifter attention that AutoGPT gets.
Feels like this newsletter is actually written by an llm. It's full of repetition and very flat assertion stitched together with high intensity random connectors. "Make no mistake [something incredibly common and already expressed here]", "Our own take on this is [another super cliche platitude here]".
I don't like how this newsletter uses "we/our" terminology - "Our personal take is that it might be beneficial to build agents that excel at some really well-defined and small-scale tasks" - without (as far as I can see) ever saying who "we" are.