Viewing profile — nutellalover
nutellalover
HN member- Joined
- Sat, Feb 23, 2019, 9:06 AM UTC
- HN karma
- 517
- Public activity
- 61 items
- HN profile
- View on Hacker News ↗
About nutellalover
No profile information was provided.
Recent public activity
- story
- story
- story
- story
- story
-
comment
Comment #46290786
Hey, I teach a class at Stanford covering among other things how to effectively use AI across the full SDLC. Hope it's helpful! https://themodernsoftware.dev/
- story
- story
- story
-
comment
Comment #41396882
Codeviz is such a cool project. Love having it in VSCode.
-
comment
Comment #41388295
Big fans of Cursor ourselves. One of the goals with this library is to make it easy for maintainers of OSS projects to expose chat support functionality to their users in a very st…
-
comment
Comment #41386411
Happy to help! At the beginning, we started with qualitative "vibe" checks where we could iterate quickly and the delta in quality was still so significant that we could obviously …
-
comment
Comment #41386395
Great question. For most small repos (10-20 source files) this works incredibly well out-of-the-box. We stress-tested with repos like langchain, llamaindex, kubernetes and there th…
-
comment
Comment #41386379
The truth is we started there. But for any reasonably-sized, complex codebase this just isn't going to work as the context window isn't sufficient and moreover it becomes harder fo…
-
comment
Comment #41386170
This is a great read Simon.
-
comment
Comment #41386143
Definitely agree that the trend is toward lower cost where a lot of these use-cases are unlocked. Especially as all the major 3rd party LLM providers scramble to ship better models…
-
comment
Comment #41386135
Thanks for the note! We welcome contributions!
-
comment
Comment #41386132
We ran some qualitative tests and there was a quality difference. In fact, benchmarks show that trend to generally hold: https://archersama.github.io/coir/ That being said, our goa…
-
comment
Comment #41385542
You can certainly apply to a private repo. If you want to ensure data stays local, you would have to add support for an OSS embedding/LLM model (of which there are many good offeri…
-
comment
Comment #41385302
Yup! We use tree-sitter and parse it at the file-level.
-
comment
Comment #41385264
Thanks! This is a great idea. Definitely something we plan to support.
-
comment
Comment #41385258
The starter config is Openai embeddings + llm, pinecone vector store, gradio for the UI. But it's customizable so you can swap out whatever you want easily.
-
comment
Comment #41385102
Feel free to submit an issue on the repo and we'll get to it!
-
comment
Comment #41385098
Thanks for the request! This is on our roadmap, as is supporting Github issues and eventually external documentation/code discussions from Slack, Jira/Linear, etc.
-
comment
Comment #41385077
OP here! I love this stress test. Will index and get back to you!