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, with more and more of the tasks handled by various AI. Fascinating.

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 can see a world where the author didn't think twice about writing down his thoughts in 15 minutes and publishing on his own personal site. Perhaps it comes naturally to people who have been around this industry longer

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 things you didn’t even think were possible. you get excited, start pushing it further. you run it and then it fails on step 17, then 41, then step 9.

now you can’t reproduce it because it’s probabilistic. each step takes half a second, so you sit there for 10–20 minutes just waiting for a chance to see what went wrong

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 definitely still tuning a couple things there.

We're not focused on simple factoid answers like population of cities because that's not where people get the most value.

AWS API is a bit tricky because it is a rather broad technology with SDKs in different languages and thus the search results for a question will return a mishmash of solutions which we then try to make sense of. If you share some sample queries you tried related to this, I'd be happy to look into them and improve our answers there.

Business model: We're currently just focused on building something developers want. Agree that ads and dev tools aren't the most synergetic.

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 system is early and will improve over time, but if can easily check if an answer is from say, the FastAPI official documentation, then the false-confidence effect of these models become less of an issue.

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 next step we're looking into is to expand sources to research papers e.g explicitly pulling from arxiv on some queries.

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 though.

The citing sources feature can definitely be improved - right now it works at a sentence granularity and insists on finding the best source when sometimes not appropriate. Thanks for pointing all of this out