Vector Search

Feeds to Scour
SubscribedAll
Scoured 142 posts in 8.4 ms

New comment by lauuuer in "Ask HN: Who wants to be hired? (June 2026)"

馃摝In-process DatabasesContent type: Discussion

I wondered how big platforms detect stolen images. So I built the whole system myself.

馃搶Embedding RetrievalContent type: Code
github.comr/sideprojects

ANN Search: Recall What Matters

馃搹ANN BenchmarksContent type: Academic
arxiv.org

Rayforce

馃搶Embedding RetrievalContent type: Code
github.comLobsters, Hacker News

Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models

馃搶Embedding RetrievalContent type: Academic
arxiv.org

New comment by t_gamer_kle in "Ask HN: Who wants to be hired? (June 2026)"

馃摝WASMContent type: Discussion

GoodQ02/goodq4all: Local-first multimodal epistemic memory for scene-level video, audio, and text intelligence.

馃摝In-process DatabasesContent type: Code
github.comHacker News

shoo99/paper-rag: A private, fully-local RAG over your own PDFs: BGE-M3 + embedded Qdrant + a local LLM via Ollama. ~150 lines, nothing leaves your machine.

馃搶Embedding RetrievalContent type: Code
github.comDEV

Adaptive Calibration for Fair and Performant Facial Recognition

馃搶Embedding RetrievalContent type: Academic
arxiv.org

Trajectory Geometry of Transformer Representations Across Layers

馃搶Embedding RetrievalContent type: Academic
arxiv.org

AIchain Skill: A Prompt as a Reusable Object

馃搶Embedding RetrievalContent type: Code
github.comDEV

Puffin-Backed Vector Indexes: Attaching Approximate Nearest Neighbor Indexes to Apache Iceberg Snapshots for Compute-Disaggregated Query Engines

馃IcebergContent type: Academic
arxiv.org

Correlation Is Not Enough: Embedding Human Metadata for Individual Causal Discovery

馃搶Embedding RetrievalContent type: Academic
arxiv.org

LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval

馃搶Embedding RetrievalContent type: Academic
arxiv.org

ahmeabd/italia-corpus: Italia Corpus - La Legge OpenSouce

馃搶Embedding RetrievalContent type: Code

Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents

馃搶Embedding RetrievalContent type: Academic
arxiv.org

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help