Feeds to Scour
SubscribedAll
Scoured 200449 posts in 30.1 ms
Digest Issue 86: Examining Constitutional AI | Pollen & Nectar | Drivers are challenging Uber with their own Denver startup. Here’s how it’s going | Practical Decentralization  🌱Sustainable Transportation
distroid.substack.com·6d·Substack
(Refer to the presentation title from co-presenter Abdul Karim) — Abdul Karim & Jack Silman at AI Engineer Melbourne 2026  💬Prompt Engineering
webdirections.org·5d
Babel: Jailbreaking Safety Attention via Obfuscation Distribution Optimized Sampling  💬Prompt Engineering
arxiv.org·2h
Researchers detail safety gaps in agentic AI systems  🤖AI Agents
kite.kagi.com·6d
Competitive Differentiation for Foundation Models in the LLM Space  🧠LLM Reasoning
mlops.community·5d
Position: AI as Part of Self -- Extending the Mind Requires Cognitive Co-Regulation  🔄Systems Thinking
arxiv.org·1d
How to Test AI Agents with LangSmith: A Complete Guide  🧠LLM Reasoning
techcommunity.microsoft.com·5d
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails  🧠LLM Reasoning
arxiv.org·2h
parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning  💬Prompt Engineering
arxiv.org·1d
Taming LLMs with NeMo Guardrails  🤖Local LLMs
mlops.community·5d
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution  🤖AI Agents
arxiv.org·2h
REBAR: Reference Ethical Benchmark for Autonomy Readiness  🤖AI Ethics
arxiv.org·2h
DeepSlide: From Artifacts to Presentation Delivery  💬Prompt Engineering
arxiv.org·1d
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening  👁️Computer Vision
arxiv.org·2h
Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction  🔢Kolmogorov Complexity
arxiv.org·2h
Reactive Robot-Centric Safety for Autonomous Navigation in Constrained and Dynamic Environments  🤖AI Agents
arxiv.org·1d
GraphMAR: Geometry-Aware Graph Learning Framework for Spatially Adaptive CT Metal Artifact Reduction  👁️Computer Vision
arxiv.org·2h
Ethical Hyper-Velocity (EHV): A Provably Deterministic Governance-Aware JIT Compiler Architecture for Agentic Systems  🤖AI Ethics
arxiv.org·2h·Hacker News
DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking  👁️Computer Vision
arxiv.org·2h
Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning  🧠LLM Reasoning
arxiv.org·2h

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