thutch76

That's fair. My attention wanted and I lost the plot.

However, I don't think having an agent on one side necessarily changes anything. Network problems are not predictable, particularly on mobile, so the human is still very likely to experience a poor auditory experience on a tcp connection.

I didn't make it all the way through the post, but I have to say I think he fundamentally understands the purpose of WebRTC. He calls himself an expert, and yeah he's written SFU's in go and rust and different companies ... but his technical credentials do not mean he's correct.

Maybe it's a comprehension issue on my end, but he seems to associate things like stun and dtls as related, compounding issues (particularly in round trip time), but they are really orthogonal.

Also, he spends too much time talking about how you can't resend packets, and reiterates that point by stating they tried really hard (at discord?). That's where he lost the plot, imo.

The RTC in WebRTC is about real time communication. Humans will naturally prefer the auditory experience of an occasional dropped packet, vs backed up audio or audio that plays at an uneven rate. To clarify, I'm talking about human speech here.

If you want to tolerate packet loss, use a protocol based on tcp instead of udp. But you know what happens when you send audio over poor network conditions with tcp? There will be pauses on the receiving end as it waits for the next correct packet. Let's say the delay is multiple seconds. What should the receiving end do when packets start flowing again? Plays the clogged audio at a natural clock? Attempt to play the audio back at a higher rate to "catch up" with any other channels? People, humans, do not generally prefer that experience.

Forget about WebRTC for a minute, but instead think about tcp vs udp for voice. Voip has been based on udp since the 90's for a reason.

I've taken a two week hiatus on my personal projects, so I haven't experienced any of the issues that have been so widely reported recently with CC. I am eager to get back and see if experience these same issues.

I love reading posts like these.

I will still reach for a database 99% or the time, because I like things like SQL and transactions. However, I've recently been working on a 100% personal project to manage some private data; extracting insights, graphing trends, etc. It's not high volume data, so I decided to use just the file system, with data backed at yaml files, with some simple indexing, and I haven't run into any performance issues yet. I probably never will at my scale and volume.

In this particular case having something that was human readable, and more importantly diffable, was more valuable to me than outright performance.

Having said that, I will still gladly reach for a database with a query language and all the guarantees that comes with 99% of the time.

This is not weaponizing to a single disabled person. I am not disabled, but I have always had difficulty expressing myself effectively, and that difficulty has increased as I've aged. I use AI to help organize my thoughts, to help give voice to that little tidbit of an idea that is trying to escape, and it has been a genuine help. Asking me to not use that assistance is similar to asking a user to not use accessibility features. It's an asinine policy and is an overcorrection.

This is awfully narrow minded. I had Claude give me an initial framework, based on the many many hours of context of chat across many different documents. It helped me organize my thoughts.

Some of us need assistance to communicate effectively. And for me, yes that took 3 hours even with this assistance.

I'm very wary of this request, though I understand it. I've been reading HN daily since around 2014. My involvement was purely passive (e.g., I have been a lurker) because I really didn't think I had much to contribute that wasn't already stated better by others.

I didn't actually create my account until 2021? 2022? I can't remember. And I didn't make my first post or even comment until just last week.

While I think a minimum post count or reputation metric could perhaps reduce the AI generated posts, introducing friction also makes it harder for real people to contribute anything meaningful.

Furthermore, what does it matter if it's "AI generated"? Is some AI content ok? What's the pass/fail threshold on human vs AI generated text?

I made a Show post last week where I heavily relied on AI. I'm sure there are some "tells." But even so, I spent more than three hours working on the content of my post and my first response. Would my post have been acceptable to you?

Builder here, happy to answer questions about any of the internals.

If you want to dig deeper on the architecture, I wrote up the dual-LLM design and the memory system on my engineering blog:

- https://www.conecrows.com/blog/augur-soft-launch — covers the dual-LLM turn loop, perception gating, and why the single-LLM approach failed - https://www.conecrows.com/blog/augur-memory-v1 — covers impression extraction, vector embeddings, and lossy synthesis

The stack is Fastify, Next.js, Supabase (Postgres + Auth), and both OpenAI and Anthropic models for the engine and analysis. Encounters cost roughly $0.08–$0.15 per turn (internal cost) depending on state complexity and encounter length.