Hacker News Reader

foxgroveron Current architectural best practices for LLM applications

Few other helpful options recently added to Langchain:

1. Extraction for query filters - https://twitter.com/hwchase17/status/1651617956881924096?s=4...

2. Contextual compression to eek more out of prompt stuffing - https://twitter.com/hwchase17/status/1649428295467905025?s=4...

And then it’s been there’s existing great utility chains for map-reduce, with re-ranking, etc for more ways to apply LLM completions over large documents and/or large sets of documents: 3. https://m.youtube.com/watch?v=f9_BWhCI4Zo

foxgroveron A Q&A with Airtable’s head of growth engineering

It's interesting to learn specifically about Growth Engineering, given so much is normally written about Growth overall as a function and those posts are typically about the PM side and tactics/experiments that teams tried. Also interesting to see where companies draw the lines of engineering responsibilities for Growth teams vs the rest of the org and how they split the team up.

foxgroveron Amplitude (YC W12) Launches a CDP

Taking on Segment (YC S11), RudderStack, mParticle, and maybe a lesser degree FreshPaint (YC S19), Hightouch (YC S19), Census, etc.

foxgroveron A story about pivots

Yes

foxgroveron Ask HN: What weird or hard problems are you trying to solve?

Sounds like Fivetran or Stitch Data. AWS released a new service, AppFlow, with a similar vision though focused on AWS ecosystem as destinations for the data.

foxgroveron Ouster's new digital Lidar – 128 beams, ultra-wide view

For those who don't know the reference :) https://en.wikipedia.org/wiki/Hyperion_Cantos