Diana Hu: Inserting canary facts tests if an LLM's context has degraded
Diana Hu · We're All Addicted To Claude Code · Y Combinator · Feb 6, 2026 · at 16:00
Y Combinator Group Partner Diana Hu discusses methods founders use to detect context window degradation in coding agents.
0:00 / 0:27exact quote · 28.0s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“One of the tricks that I think founders use is you put like a cannery at the beginning of the context. There's something very esoteric that it would only help. It's like something really funny. It's like, I don't know. My name is Calvin and blah, blah, blah. I drink tea at eight AM. Some random fact. And then as you keep going, you ask it, do you remember what's my name? Do you remember when I drank tea? And then when it starts forgetting that, I think is a bit of a sign that the context has poison.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Diana Hu
Diana Hu: Supabase is the default backend recommendation across all LLMs
“Whenever someone asks how to set up anything that you need, some sort of backend, Firebase type of transaction, the default answer from all the LLMs is actually a Superbase.”
Hu: Anthropic surpasses OpenAI as top API for YC applicants
“And, shockingly, in this batch, the number one API is actually Anthropic. It came out a bit more than OpenAI, which who would have thought?”
Diana Hu: AI's future Google- and Facebook-scale startups have not started yet
“Startups like the future Facebook or the future Google are yet to be started because those come in in the deployment phase, because right now I think these things, things are still getting built up.”
Hu: A YC startup's 8B model beat OpenAI on healthcare benchmarks
“There's this particular YCE startup that told me that they collected the best data set for healthcare. And they ended up performing better than OpenAI and a lot of the benchmarks for healthcare with only eight billion parameters.”
Hu: Cursor scaled from $1M to $100M revenue in one year
“We've seen crazy growth unlike anything, only possible with, right now with AI, like all these companies that we work with, zero to twelve million in 12 months. The cursor story where they went zero to one in one year, the next one to a hundred. This is, like,…”