swaminarayan

How does this perform on longer videos, especially on lower-end machines? Is the transcription and video processing entirely local in the browser?

How it select model? using AI?

I am getting used to with this lightrag-snkv, Now I dont need to check hacker news site again, it automatically ingest top ranked posts and I can query and check answers using natural query language.

I am pasting link here: https://github.com/user-attachments/assets/23a95319-ee66-49b...

if you are opening video in mobile github app then it won’t open.Check in browser.

Right now Show HN and Ask HN tags based blogs and its comments are ingested in database.

this is not mythology. this is ithihasas meaning thus it happened

Found my answer: https://github.com/google-ai-edge/gallery?tab=readme-ov-file

i like this idea, especially for the parent who dont want their kids to watch reels/shorts of the instagram and youtube apps.

lol

What architectural decisions enabled pg_textsearch to outperform Tantivy/ParadeDB by 4.7×, especially given Tantivy’s reputation for speed?

Interesting approach — especially around modifying SQLite’s internals.

In SNKV, I’m taking almost the opposite direction: keeping B-tree / storage-layer ideas and removing the SQL layer entirely, to expose a minimal key-value interface.

Curious how you think about the tradeoff between simplifying the query layer vs the storage layer.

https://github.com/hash-anu/snkv

Really interesting design — especially using SQLite-compatible storage with a PostgreSQL interface.

I'm working on SNKV, which explores a different approach: skipping the SQL layer entirely and focusing on a simple key-value interface.

It works closer to the storage layer (b-tree / WAL / pager concepts), aiming for a lightweight and minimal design, while supporting multi-process access.

Curious how you think about the tradeoff between SQL flexibility and a simpler KV interface.

https://github.com/hash-anu/snkv

Very cool approach. I’m working on a related KV storage project (snkv - https://github.com/hash-anu/snkv)

How do you handle manifest consistency and updates—append-only or rewrite-heavy?

What were the biggest architectural changes in the rewrite, and what tradeoffs did you make compared to the old Video.js design?

Does your method work better than standard ANN when filters are very strict—and how does it affect speed vs accuracy?

How do you build a procedurally generated survival game in a terminal without a graphics engine?

How did you make a very small AI model (14M) sound more natural and expressive than even bigger models?

if you want to use key value store using sqlite then you can try : https://github.com/hash-anu/snkv

in which i am directly accessing b-tree layer and not consuming query layer.

for kv workloads it is much faster compare to sql.

and yeah you will get same benefits of sqlite storage engine.

What would you do if your entire Git history was instantly queryable with SQL?

What do we gain and lose by treating AI agents like software projects in Git?

Why do minimal apps sometimes work better than feature-rich ones?

makes sense

Why do AI agents get worse with more context, and how should we manage context windows?

Could a K-style array language be a practical way to design audio waveforms and DSP patches?

If a working compiler can be written in ~1000 lines, why are production compilers like GCC or LLVM millions of lines?

How do you defend against prompt-injection attacks that cause the agent to call legitimate endpoints but exfiltrate sensitive data through the response?

26% of AI coding sessions are abandoned within 60 seconds .Is this a prompt problem, a tooling problem, or a limitation of current models?

AI coding agents can execute shell commands. what’s the safest way to control them in production?

Axe treats LLM agents like Unix programs—small, composable, version-controllable. Are we finally doing AI the Unix way?