Viewing profile — brianjkim21
brianjkim21
HN member- Joined
- Thu, Feb 24, 2022, 6:46 AM UTC
- HN karma
- 13
- Public activity
- 33 items
- HN profile
- View on Hacker News ↗
About brianjkim21
No profile information was provided.
Recent public activity
- story
- story
- story
-
comment
Comment #41074227
this is sick, thanks for sharing
-
comment
Comment #41074083
thanks roanak!
-
comment
Comment #41002477
PMs and Execs are pushing devs to do docs classification and extract data from text ("see I can do it on chatGPT!") so they're using Taylor (trytaylor.ai) to build production grade…
- story
- story
- story
- story
- comment
- story
- story
-
comment
Comment #40348155
thanks :) you too!
-
comment
Comment #40348105
thanks! primarily classical. we designed an ensemble that considers both lexical & semantic similarity and trained on large datasets of labeled text. we train our own 'out-of-the-b…
- story
- story
- story
- story
- story
- story
-
comment
Comment #40055477
Example? To clarify, I'm referring to product eng and SWEs. If you have a Data / ML team, they will handle ofc.
-
story
Ask HN: Are engineers afraid of free text?
Text classification isn't new. Yet, very few product & eng teams actually do text classification. Do you build text classification models in house? Why do you think eng teams with …
-
comment
Comment #39750619
thanks. yup, it's on our roadmap :)
-
comment
Comment #39750579
yup, we designed an ensemble that considers both lexical & semantic similarity and trained on large datasets of labeled text. also building data pipelines to prevent models going s…