Agree it's divisive, and I would argue it speaks more to a person's perception of work vs play more than a relationship to tech. If (the general) you think that play is for children and work is serious biz, then yeah I could see how you wouldn't take someone seriously when they say they're "playing around with it". It's usually not obvious which attitude a person has though without getting to know them a little bit.
Language choice had less impact than people first assume even before LLMs in most software. A good engineering team produces good code in whatever language they happen to be using. In my own career I've worked in serious Java, Scala, Haskell, Javascript, PHP, and Python application stacks and I've seen plenty of good and bad examples.
I reckon language choice matters more at the edges of economic activity where a specific language feature really does make the difference in the end product, but most activity that is leveraging LLMs now is more generic enterprise SaaS software.
IME Python has been very pleasant to use with types, even though they are not nearly as expressive as Haskell. I've noticed a shift in my own work where I spend more time playing with/manipulating change than I do making sure things type check. That does happen, of course, but it happens with less frequency then when I was writing Haskell by hand. During that time, I'd have stack running tests on file change and it was pretty smooth as well, but that workflow breaks down a bit with the current generation of agent harnesses we have.
Are you one of the folks thinking of upgrading? If so, from what generation? What makes you excited? Isn't this a more interesting way to have the conversation?
Are you familiar with ACP[0]? Through that protocol you can run claude code within zed[1]. Or perhaps I'm not understanding what you mean by using CC integration.
ACP is so much worse than Claude Code CLI - the quality is not there. Everyone assumes the JSON-CLI-API is the same as the CLI but it is not. Tool usage is different, and I assume agent system prompts are different and agents are different.
Integration like in Cursors, I use the CLI and Claude Code knows what files are open, uses Cursor for diffs etc.
You can see an example of the Chain of Thought in the post, it's quite extensive. Presumably they don't want to release this so that it is raw and unfiltered and can better monitor for cases of manipulation or deviation from training. What GP is also referring to is explicitly stated in the post: they also aren't release the CoT for competitive reasons, so that presumably competitors like Anthropic are unable to use the CoT to train their own frontier models.
> Presumably they don't want to release this so that it is raw and unfiltered and can better monitor for cases of manipulation or deviation from training.
My take was:
1. A genuine, un-RLHF'd "chain of thought" might contain things that shouldn't be told to the user. E.g., it might at some point think to itself, "One way to make an explosive would be to mix $X and $Y" or "It seems like they might be able to poison the person".
2. They want the "Chain of Thought" as much as possible to reflect the actual reasoning that the model is using; in part so that they can understand what the model is actually thinking. They fear that if they RLHF the chain of thought, the model will self-censor in a way which undermines their ability to see what it's really thinking
3. So, they RLHF only the final output, not the CoT, letting the CoT be as frank within itself as any human; and post-filter the CoT for the user.
reply