Post-training methods for language models
developers.redhat.com·3d
💬Prompt Engineering
Flag this post
Enterprise Data Access: Fully Automated Soft-Delete
byteaether.github.io·18h·
Discuss: DEV
🗄️Database Internals
Flag this post
Benchmarking the cost of Java's EnumSet - A Second Look
kinnen.de·2d·
📏Linear Types
Flag this post
Free Weather Data with National Weather Service API
clojurecivitas.github.io·8h·
Discuss: Hacker News
🔌APIs
Flag this post
Dynamic Neuro-Network Resilience via Stochastic Gradient Amplification and Adaptive Sparsity (DNSAS)
dev.to·23h·
Discuss: DEV
🔬Deep Learning
Flag this post
Building a Smart Task Tracker Agent for Telex.im with ASP.NET Core
dev.to·1d·
Discuss: DEV
🤖Automation
Flag this post
Large language models require a new form of oversight: capability-based monitoring
arxiv.org·1d
🚀MLOps
Flag this post
AILA--First Experiments with Localist Language Models
arxiv.org·1d
📝Parsing
Flag this post
Epidemiology of Large Language Models: A Benchmark for Observational Distribution Knowledge
arxiv.org·1d
🤖Transformers
Flag this post
A Simple and Repeatable Approach to Evaluating LLM Outputs
dev.to·1d·
Discuss: DEV
💬Prompt Engineering
Flag this post
Build123d (A Python CAD programming library) Roadmap
github.com·1d·
Discuss: Hacker News
🎨Design Systems
Flag this post
The Art of the Do-Over: Designing Idempotent Jobs as a Journey to Peace of Mind
dev.to·3d·
Discuss: DEV
🔧DevOps
Flag this post
Show HN: Tool2agent – a protocol for LLM tool feedback workflows
github.com·10h·
Discuss: Hacker News
💎Refinement Types
Flag this post
About AI and context
dev.to·1d·
Discuss: DEV
💬Prompt Engineering
Flag this post
Taming AI Hallucinations: Solving Physics with Reality Checks by Arvind Sundararajan
dev.to·1d·
Discuss: DEV
📱Edge AI
Flag this post
Vibecoding and the future of code security
dev.to·13h·
Discuss: DEV
🎭Program Synthesis
Flag this post
Sub-exponential Growth in Online Word Usage: A Piecewise Power-Law Model
arxiv.org·3h
📊Data Science
Flag this post
Ariadne: A Controllable Framework for Probing and Extending VLM Reasoning Boundaries
arxiv.org·3d
🧮SMT Solvers
Flag this post