| ▲ | mathijs 7 hours ago | |
I've used simpler agents like Copilot and Devin/Windsurf/Cascade/whateveritiscallednow, mainly in IntelliJ, and depending on the model, they starts showing behaviour that is at least remotely like this. Example: put the agent in Ask mode (so it can't edit files) and you'll see it try to edit files anyway. The train of thought shows "something went wrong editing the file, let me try a different way" and it'll start spewing out bash files or Python scripts that try to edit a file. None of it works or can be executed, but still. Cheaper models often ignore the available function calls to find and edit files in the IDE, and will start asking for permission to execute grep and sed commands, as well as trying to echo entire bash or Python scripts to file again. It is not exactly like an agent autonomously trying to hack Huggingface, but it is a way of frantically looking for a solution because 'giving up' is not what LLMs are trained for. | ||
| ▲ | jbjbjbjb 3 hours ago | parent | next [-] | |
When it does that I feel like it is the clearest example of how dumb these things actually are. Often it takes what you prompted, identifies something as unclear, writes a bunch of chain of thought reasoning around it and just goes off hammering your tokens and just executing commands and repeats this. I’m not going to pretend to be an expert in these things but that process seems deeply flawed - and why can’t something just stop the loop? If that was a real employee it would be reasonable to expect the employee to ask for clarification, not go down expensive rabbit holes and, of course, not break any laws. | ||
| ▲ | Rapzid 4 hours ago | parent | prev [-] | |
Even the frontier models might do that on occasion. I just tell them to use the tools and it gets them back on track. | ||