Chinese researchers let LLMs share meaning through internal memory instead of text
the-decoder.com·1d
⚡Cache Coherence
Joy & Curiosity #57
registerspill.thorstenball.com·1d
🏺ZIP Archaeology
Pretendo
pretendo.network·12h·
Discuss: Hacker News
📼Retro Games
Erlang-Red Walkthrough – Visual FBP for Telecom: Diameter AAA on Erlang/OTP
blog.tadsummit.com·3d·
Discuss: Hacker News
🌐Protocol Synthesis
Don't Buy Antivirus, Use an LLM Instead
gxenos.github.io·5h·
Discuss: Hacker News
🦠Malware Analysis
“I Consider Myself,” by Natan Last
newyorker.com·11h
⭐Awesome lists
The Trillion Dollar AI Software Development Stack
a16z.com·2d·
Discuss: Hacker News
⚡Proof Automation
Enhanced Predictive Maintenance for 3nm FinFET Gate-All-Around Structures via Bayesian Dynamic Network Analysis
dev.to·1d·
Discuss: DEV
🔧Hardware Verification
Reimagine Libraries management as Apps using Agentic Executable framework
dev.to·20h·
Discuss: DEV
🧱Immutable Infrastructure
CaRT: Teaching LLM Agents to Know When They Know Enough
arxiv.org·3d
🔲Cellular Automata
HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
arxiv.org·3d
⚡Proof Automation
LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
arxiv.org·3d
🔲Cellular Automata
Training Models to Detect Successive Robot Errors from Human Reactions
arxiv.org·17h
🧠Machine Learning
Recurrent Natural Policy Gradient for POMDPs
arxiv.org·3d
🔲Cellular Automata
SAM2-3dMed: Empowering SAM2 for 3D Medical Image Segmentation
arxiv.org·17h
🌀Riemannian Computing
A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?
arxiv.org·17h
🧠Intelligence Compression
Latency vs. Accuracy for LLM Apps — How to Choose and How a Memory Layer Lets You Win Both
dev.to·6d·
Discuss: DEV
⚡Performance Mythology
Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
arxiv.org·5d
🧠Machine Learning
Tech With Tim: Cancel Your AI subscriptions | This All-in-one AI is All You Need (ChatLLM Review)
dev.to·6h·
Discuss: DEV
🎙️Whisper
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·1d·
Discuss: DEV
🦀Rust Macros