alt Hacker NewsThis matches my experience with Astra so far too.
> I think I’m suspecting something is going “wrong” in the training process. The model is greatly rewarded for succeeding on long-horizon tasks, but presumably there is very little punishing going on for “shitty code.”
My suspicion is that both OpenAI and Anthropic moved their RL agendas from "being rated as useful according to human feedback" to "succeeds at long horizon tasks" in the last few months, resulting in agents that are closer to AGI in an autonomous task-completing sense, but strangely bad at communicating.
The result is that they are amazingly good at long horizon tasks, computer use, solving difficult math/ARC-AGI type problems, but becoming weirder and weirder to work with.
Replies
I wonder too if in training for long horizon tasks agents become worse team players, good at orchestrating subagents they are trained to use, but worse as an agent within an external multi-agent orchestration system or just in turn-taking with humans. That was my experience with Opus 5 and so far it has been my early experience with Astra as well.
I wouldn't be surprised if they are optimising for producing more code, because in the long term, more existing code means they can sell you more tokens to maintain it.
So the AI equivalent of the socially stunted but brilliant researcher?
I wonder if we will start using LLMs to translate the output of other LLMs to make it more palatable for humans.
so they trained it to be a 10x engineer?
> This matches my experience with Astra so far too. > I think I’m suspecting something is going “wrong” in the training process. The model is greatly rewarded for succeeding on long-horizon tasks, but presumably there is very little punishing going on for “shitty code.”
Probably because so many influencers in the space say stupid things like: “it works, right? Why would I spend time reviewing ai generated code?” As if the junior engineer who wrote over engineered complex and sometimes bad code — if they had just done it faster — would somehow be acceptable. wtf?
They don’t want to sell these tools to developers. They want to cut as many layers as possible.