Viewing profile — rahulb0802
rahulb0802
HN member- Joined
- Wed, Jul 08, 2026, 3:02 AM UTC
- HN karma
- 1
- Public activity
- 8 items
- HN profile
- View on Hacker News ↗
About rahulb0802
Github: https://github.com/rahulb0802
Recent public activity
-
comment
Comment #49075744
What does the actual path to deployment look like? Do I connect a repo, copy paste code, or something else?
-
comment
Comment #49075676
How did you assemble your training dataset, especially since you mention some of the considerations with different training mixes in your controlled eval?
-
comment
Comment #48873094
[dead]
-
comment
Comment #48868405
I really like the clustering aspect of this. It would be cool if there was a way to articulate some sort of relationship between two adjacent or nearby papers in this tool.
-
comment
Comment #48854683
[dead]
-
comment
Comment #48832189
I like the approach; avoiding a model call just to summarize old context while keeping the cache warm is a nice property. When it folds away an older chunk of the conversation, doe…
-
comment
Comment #48832126
[dead]
-
comment
Comment #48832012
This is cool! One question: is the format documented anywhere, or a stable enough schema that someone could write, for example, a script that pulls last week's jots into a review? …