Hacker News Reader

Comment by yaohui-wyh | Hacker News Reader

This article has been around for some time, and it still shines. It focuses on building a product rather than just prototyping an LLM wrapper and waiting for the dark magic of GenAI.

Chapters like "The Strive for Faster Latencies" and "Post-Processing" are truly inspiring.

Creating production-level DevTools demands much more effort than merely wrapping around a ChatCompletion endpoint and mindlessly stuffing a context window with everything accessible inside the IDE (so-called "prompt engineering").

View on HN

I attempt to use LLMs in coding tasks many times a day, the capability is there: Opus can make and execute a plan, GPT-4 can find and fix a few persistent typographical errors when Opus attempts verbatim output, and Dolphin-8x7 (or a bunch of other consistently candid models) can de-noise out the static interference from the Morality Police over-aligment.

For a long time it’s been about extravagances like the ability to recover from a lost session, or get a link queried and used as context, or do a reset of the slowly but inevitably corrupted state without losing all of your painstaking assembled point in some abstract state space.

Basic product building on the core LLM experience is way more important than incremental improvements on LLMs, I’d take robustness, consistency, and revision control over an LLM breakthrough, a chat bot session is a tech demo if I lose my work with my browser tab.

These folks get it, I agree.

> This article has been around for some time, ..

Interesting, what gave you this impression? This article was first published only 4-6 months ago around Oct 2023.

Don't get me wrong, I'm a fan of sourgraph and their founder, Quinn, is quite charismatic. I almost went for a job offer with them 5+ years ago. But let's be real, startups are not a winning game for a non-founder, thank goodness I stuck it out with BigCorp. In any case, this isn't that old of a post, cheers.

They seem to have got the correct impression that it's been "around for some time" as "some time" does not mean "a very long time" and you just confirmed that it indeed isn't a just-published article but one which, coming out last year, has been around "for some time".

I'm guessing you're just reading into the phrase an implication that isn't there about it being particularly old.

"Some time" does have pretty much that implication. The exact amount of time is unspecified, but I'm unsure that 6 months is enough to count. Maybe this is an American vs British English thing?

You dan't have to trust me: https://dictionary.cambridge.org/dictionary/english/for-some...

Well, you could argue that in the fast-evolving AI domain 5 months is already "a fairly long period of time"...

> startups are not a winning game for a non-founder, thank goodness I stuck it out with BigCorp

I'm curious why you think a big corporation has a higher expected value than a startup.

Because their equity compensation is in liquid stock (RSUs) rather than stock options.

https://danluu.com/startup-tradeoffs/

Can confirm.

Spent the last 5 years at 2 different startups.

Presently unemployed and broke due to literally worthless equity.

Reply on news.ycombinator.com