Viewing profile — wayy

I came across this PR with many different systems kicking off AI reviews, comments, and changes. You can also see human devs chiming in. This is the future of how people will work,…

Hey all, Justin here. I previously built Phind, the AI search engine for developers. One of the biggest problems we had there was figuring out what went wrong with bad searches. We…

It seemed to me the author was simply sharing his own lived experience, which happens to be a bit contrarian to the popular hype around LLMs. It may seem courageous for some but I …

everybody loves building agents, nobody likes debugging them. agents hit the classic llm app lifecycle problem: at first it feels magical. it nails the first few tasks, doing thing…

Hey HN, I'm learning Chinese and grew tired of rote memorization and the contrived examples found in many language-learning apps. I wanted to learn in a more natural context by rea…

Justin and Avichal here. We’re building Linden ( http://trylinden.com ), a tool for maintaining browser automations at scale. Avichal lived this problem at a dental insurance start…

Thanks for pointing this out - we didn't consider how important stackoverflow comments could be. Will look into including as a source.

Ah we only put the option for detailed comment on negative feedback (try clicking the x and a form will pop up). Will also give that option for positive feedback in the future.

Thanks for trying it out! We can definitely be clearer on our focus for programming related queries. We usually don't display code snippets for non-programming questions but defini…

The answer is based on the contents of the websites returned by the search engine + other some sources.

What is the correct/expected answer to that query?

We think the solution is simply having good sources and answer transparency. If you mouse over part of the answer, we try to show you the source of that sentence. Obviously this sy…

You're right - there are so many good sources not often surfaced by a cursory web search like books and experts. Adding better sources is something we're improving on. A simple nex…

Interesting, we are trying to wrangle with the nondeterminism but sometimes it can't be helped as Bing itself can produce different results. Always actively working on the model th…

If you can't find the information yourself via a web search, it's going to be difficult for the model to find the answer too... for now ;)

You can leave feedback on individual search results via the check and X buttons below the answer. Leaving feedback e.g votes on each code snippet is on the roadmap.

Exactly, we use some information from traditional search engines as input to our model.

Thanks for trying it out - we're still quite early so the model isn't going to be perfect + we're focused on programming related queries at the moment. What is your use case? Are m…

The answers are explicitly based on information found on the web instead of some knowledge found within the model parameters.

yep, it's super interesting to watch how cheap and plentiful compute starts to change the way we live

We're always actively exploring different prompting - a general question answering prompt most definitely won't work for all searches. Finding what people agree on and disagree abo…

The p50 time is around 2s end to end not under load. Bear with us as we scale our systems!

If you mouseover the answer paragraph, you'll see the relevant url / search result. You can click to go to that source.

Thanks for pointing this out - determining when code snippets are relevant is something we're actively working on.