HackerTrans
TopNewTrendsCommentsPastAskShowJobs

manoj079

3 karmajoined el año pasado

Submissions

81.1% vs. 13.6%: measuring retrieval accuracy for AIcoding context without embed

manojmallick.github.io
5 points·by manoj079·hace 2 meses·2 comments

Show HN: SigMap – 81.1% retrieval hit 5, 96.9% token reduce,zero deps

github.com
14 points·by manoj079·hace 2 meses·4 comments

[untitled]

1 points·by manoj079·hace 3 meses·0 comments

Show HN: SigMap – shrink AI coding context 97% with auto-scaling token budget

github.com
4 points·by manoj079·hace 3 meses·7 comments

comments

manoj079
·hace 2 meses·discuss
Yes , it will work.
manoj079
·hace 2 meses·discuss
[flagged]
manoj079
·hace 2 meses·discuss
Thanks! Happy to go deeper on any part — the TF-IDF ranking logic, the import graph construction, or the benchmark methodology. What are you working on?
manoj079
·hace 2 meses·discuss
[flagged]
manoj079
·hace 2 meses·discuss
[flagged]
manoj079
·hace 2 meses·discuss
* * *
manoj079
·hace 3 meses·discuss
[dead]
manoj079
·hace 3 meses·discuss
Yes. Flask goes from 242,600 tokens down to 3,400 — 98.6% reduction. Django, FastAPI, any Python project works the same way. The Python extractor captures functions, class methods, dataclass fields, and Pydantic BaseModel fields including return types.

npx sigmap — no config needed.
manoj079
·hace 3 meses·discuss
Yes, completely. SigMap runs entirely on your machine — no API calls, no cloud, no telemetry. It reads your files and writes a context file locally. Works on a plane, in a VPN-locked environment, anywhere.
manoj079
·hace 3 meses·discuss
[dead]
manoj079
·hace 3 meses·discuss
[dead]