tjohnell

This seems like a big deal.

How come I never see these threads when Nasdaq has a banger of a day? Stocks fall faster than they rise - it's not useful discourse to panic every time there's a correction. Give it a few days and we'll be back where we were.

A C2 level diagram included in the blog post would be helpful. What are the drawbacks to using Neki aside from the obvious (new software has bugs)?

Hi all - I posted about Pike several months ago that garnered some attention and wanted to follow up with my project that spun off from that - creating an open dataset for U.S. interstate highways powered by OpenStreetMap data.

I'm fully prepared for one of you to crush my soul and link me to a dataset that already exists that would have made this project dead simple. I was unable to find really simple interstate data that provided directional corridors, ordered exits, and POIs with reachability & drive-time, so I made it for Pike and now I'm making it available to YOU!

Who knows - this could be the last model we see from Anthropic. Or it just becomes the wild west and we figure it out as we go.

I’m good with just tailscale and self-hosted web-apps. Seems the main selling point is either native UX or reduced barriers to entry security-wise. I like barriers to entry.

It will inevitably learn how to think in a way that translates to one (moral) meaning and back but has an ulterior meaning underneath.

I’ve been doing a ragtag version of this with sub-agents, TTS, and STT in Claude Code. Real-time would be pretty awesome, even if it’s just orchestrating other agents. I’m might have to try this on top of my Claude agents. I don’t think the model doing the talking necessarily needs to do the heavy reasoning - just needs to have context on your other agents, delegate, and remain present.