Generative AI

Feeds to Scour
SubscribedAll
Scoured 365 posts in 8.7 ms

Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs

 💉Prompt Injection
lesswrong.com·

LLM-Based Code Documentation Generation and Multi-Judge Evaluation

 🤖AI  Content type: Academic
arxiv.org·

You’ve Been Using AI for Years. You Just Didn’t Call It That.

 🧠LLMs  Content type: Blog
medium.com·

| Amine Raji, PhD

 ⚙️Prompt Engineering
aminrj.com·

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

 🧠LLMs  Content type: Academic
arxiv.org·

Local LLMs, Buy a GPU, and the Case for Cognitive Security

 🤖AI

When LLMs Invent Rust Crates: An Empirical Study of Hallucination Patterns and Mitigation

 📚CS Research  Content type: Academic
arxiv.org·

DataXflowGen for GenAI-driven model generation

 ⚙️Prompt Engineering  Content type: Academic
nature.com·

AI Pentesting Roadmap: Labs, Challenges, Writeups & Research

 💉Prompt Injection  Content type: Blog
osintteam.blog
·

STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation

 👁️Computer Vision  Content type: Academic
arxiv.org·

mingusb/transformer-golf: The Fully Unrolled Transformer: An experimental repository for architecture simplification and compilation. [2026]

 🤖AI  Content type: Code
github.com··Hacker News

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

 ⚙️Prompt Engineering

Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles

 📚CS Research  Content type: Academic
arxiv.org·

CryoDiff: An uncertainty-aware diffusion model for Cryo-EM map enhancement

 🧠LLMs  Content type: Academic
biorxiv.org·

Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature Optimization

 🔬ML Research  Content type: Academic
arxiv.org·

AI prompting is creating a new form of digital anxiety | Technology

 ⚙️Prompt Engineering
devdiscourse.com·

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

 🧠LLMs  Content type: Academic
arxiv.org·

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

 💻Software Engineering

Reve 2.0 shows image generation is still open for startups

 🎨Creative Coding
startupfortune.com·

One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·
Sign up or log in to see more results

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