Viewing profile — christinetyip

Excited to try out its capability, especially audio and video. It's nice that it has a long context window, but in practice, I find I always have to clear context btw 150k-400k con…

Have you by any chance also tried GPT-5.6 Sol? Curious how that compares.

Shameless plug: a friend and I started Superlinear today, a short-form podcast about emerging practices for building with coding agents. Ep 1 is a 13-minute conversation about spat…

[dead]

It's been a bit disruptive to my workflows tbh. What alternatives are people using? Sell them to me please

The github repo isn't public.

Not leaking codenames is one thing, but explicitly removing signals that something is AI-generated feels like a pretty meaningful shift.

We ran an experiment over the weekend to explore whether multiple autonomous agents could collaboratively optimize inference on Apple’s Neural Engine (ANE). Each agent ran locally …

Cool, what’s a good first task to try this on where it’s likely to beat a single agent?

That makes sense, and I agree that for a single agent using skills well, Claude’s native context handling has gotten much better. This wasn't mentioned in the first post, but the u…

I mostly agree with this, if the goal were “better persistent memory inside Claude Code,” that wouldn’t be very interesting. For a single agent and a single tool, keeping project s…

You’re right that reading the same markdown file is trivial, that’s not the hard part. Where it stopped being trivial for us was once multiple agents were working at the same time.…

A lot of the discussion here is about memory inside a single tool, which makes sense. I’m curious how people think about portability: e.g. letting Claude Code retrieve context that…

Yep, parsing logs + async RAG works fine if you’re staying inside a single tool. The issue we ran into when building agent systems was portability. Once you want multiple agents or…

This is fair, many memory projects out there boil down to better summaries or prompt glue without any clear way to measure impact. One thing I’d clarify about what we’re building i…