cpt's Top FindsLoading...
More choice, more control: self-deploy proprietary models in your VPC with Vertex AI
cloud.google.com·1d
🎰Bytecode VMs
Introducing the Gemini 2.5 Computer Use model
blog.google·6h·
Discuss: Hacker News
How to *actually* test your readme
shkspr.mobi·14h·
My First Contribution to Linux
vkoskiv.com·1d·
🖥️operating systems
Domain Driven Design in Clojure with Generalized Hiccup
biotz.io·4d·
📐Language Theory
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
arxiv.org·21h
⚙️Compilers
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
arxiv.org·21h
🧩programming
Delimited Continuations in Lone Lisp
matheusmoreira.com·4d·
🧩programming
MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
arxiv.org·21h
⚙️Compilers
SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling
arxiv.org·21h
⚙️Compilers
DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
arxiv.org·1d
⚙️Compilers
Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
arxiv.org·21h
📐Language Theory
Constraint Satisfaction Approaches to Wordle: Novel Heuristics and Cross-Lexicon Validation
arxiv.org·1d
📐Language Theory
Relative Code Comprehensibility Prediction
arxiv.org·21h
🧩programming
Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
arxiv.org·1d
⚙️Compilers
Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
arxiv.org·21h
📐Language Theory
Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
arxiv.org·21h
⚙️Compilers
Vector Trifference
arxiv.org·21h
📐Language Theory
Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions
arxiv.org·21h
📐Language Theory