Anyone have a link to a video of it in action?

i'll prob add over wkd hadn't bothered as still making changes

Privilege is working at a startup

So cool! Gave me some motivation to record more things.

It amazes me that people are still interested in MCPs.

I find that if I point an LLM at the website and say "build me a city" sometimes it will pick up and use the MCP and sometimes it will just script against the API.

Wow

I have a hard time trying to poke holes in this. Seems objectively good and like it, or some very similar version of it, will work long term.

If models really do continue to get more expensive then it's not going to make sense to let everyone at your org have equal budget for spend. We're on track for a world where there are the equivalent of F1 drivers for ai.

One persons output doesn't scale for an entire org no matter how expensive and good the AI is. It's either good enough that anyone can do it, or bad enough that a human needs to be in control which caps the output at human understanding. It will always be more efficient to have every engineer be boosted a little bit than a single one a lot.

Fascinating platform. The API surface is much richer than I would have expected. Ooc, at what size do you think teams typically have use for this? I imagine you have to be running quite a few agents at scale before there's a strong usecase.

Just like codex or opencode provide strong oss implementations of the core agent loop, our ambition (not achieved! hoping this is a solid start) is to provide a solid oss implementation of the context updating loop, memory, basic database + a backend sync layer. And evals + continual learning + gepa optimization.

Just like everyone can write their own agent, yet many opt for codex/claude code sdk/opencode, we think that at some point in our journey, many will also opt for standard implementations of these patterns, for projects big or small.

Realistically, though, the case for a standardized environment grows a lot stronger when you have multi-agent, permissioned actions, and generally just a lot more state than what you can get away with using only opencode + some glue. Insofar as big teams have ambitious products, they might be more likely to try it

this is fascinating! cool ship

Thanks bud! Yeah, I thought it surfaced some really interesting stories and it kind of reminded me of pagerank like focusing on the links between things.

I think I could take it even further by doing some kind of like betweeness centrality analysis to sort of rank the most interlinked stories within the hacker news cohort, but this was like the first cut to just demonstrate that these human intelligence annotations (the related comments) could usefully cluster the stories in a way that resulted in an interesting presentation. And I think we achieved it!