Maybe because it is not such an easy problem to solve? With so many people working of quantizing and fine tuning open models, I don't buy that it is a 4-8 hour task.

I would also be genuinely greatful if someone could post how they fixed the looping issue through sampling settings without significantly sacrificing reasoning effort and context size.

Fixing this problem would result in more tickets from accounts flagged as "bad actors." So first you pay for fixing the problem, and then you pay to resolve the tickets. Maybe nobody at LinkedIn wants to pay for it?

It sucks for those banned erroneously.

Naturally, it is not in LinkedIn’s interest to change this; the corporation’s behavior is logical and understandable. But that’s not the real question. What about the community’s reaction? Has this simply been accepted as a given—normalized and justified? And what about the rank-and-file support staff who send you a template—telling you that you’re writing from the wrong email address and that you should use the one linked to your account—do they know they are peddling a blatant lie? Or do they not know? Or perhaps they simply choose not to know? "We were just following orders; we didn't know anything." I am narrowing the scope of the issue as much as possible: I am not discussing why accounts end up "restricted"—whether that’s fair or not—nor am I addressing other problems. I am focusing solely on this one specific aspect.

Your experience reminded me of Terminal Bench 4, where Terra 5.6 is much closer to Luna 6 then Sol 6. https://benchlm.ai/benchmarks/terminal-bench-4.

Looking at newer models, Terra 6.1 is only a hair behind Sol 6.1, hopefully making it a useful Sol replacement for slightly easier tasks.

Reviewing 150k loc line-by-line is not practical. I think we need a new set of tools to facilitate such tasks.

Otherwise, we will be spending most of our time monitoring AI's code writing process.

I am curious about Pi, but my experience with a seemingly more fully-featured Hermes has been endless tinkering and fixing minor issues. Have your experience been at all similar?

I've been using it without thinking much about it for 3 months now. Have yet to run into any bugs or strange behaviors. But bear in mind I'm using oh-my-pi, not Pi. I found the latter to be mostly useless in terms of what I needed for my day to day work. I'm sure I could tinker with it to get it right, but that's literally what oh-my-pi is doing for you. And like I said, zero problems thus far.

I don't know if people hate it, but I don't use it because it is overpriced (you need the $50 pro subscription to do more than tinker) and it had multiple CVEs this year. There are also a lot of n8n "influencers" on YouTube, but that is not n8n's fault.

I think it is fine for prototyping if someone prefers a GUI.

Is "the whole thing" referring to the "current system"or something else? Asking out of curiosity, as I am sadly not a younger American.

Nice. I will give it a try too. Thanks!

Handy worked fine for me on Windows, but on Fedora, I can't get it to work at all.

Unless it is something with the playback on my end, your animations and scrolling are a bit jerky too.

I like this. It means a human was involved.