OpenAI, Claude, Llama, local llms, Python

Cutting LLM Batch Inference Time in Half: Dynamic Prefix Bucketing at Scale
daft.ai·5h·
Discuss: Hacker News
High Performance Computing
Flag this post
AI Function Calling: Composing and Decomposing Functions for Complex Tasks
lightcapai.medium.com·4h·
Discuss: Hacker News
💻Programming
Flag this post
Topographical sparse mapping: A training framework for deep learning models
sciencedirect.com·2h·
Discuss: Hacker News
High Performance Computing
Flag this post
Choosing the best AI coding agent for Bitrise
bitrise.io·1h·
Discuss: Hacker News
🏛️Software Architecture Patterns
Flag this post
DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models
arxiv.org·1d
💻Programming
Flag this post
OpenAI signs massive AI compute deal with Amazon
arstechnica.com·1d·
Discuss: Hacker News
High Performance Computing
Flag this post
We need to give LLMs human-like vision
matml.bearblog.dev·6h·
High Performance Computing
Flag this post
Writing an LLM from scratch, part 26 – evaluating the fine-tuned model
gilesthomas.com·1d·
Discuss: Hacker News
💻Programming
Flag this post
The Case That A.I. Is Thinking
newyorker.com·1d·
Discuss: Hacker News
High Performance Computing
Flag this post
AI Uses Functions to Fetch Real Data (Not Just Chat)
farukalpay.substack.com·9h·
Discuss: Substack
💻Programming
Flag this post
Show HN: Refusal-Aware Logical Framework for LLMs
github.com·7h·
Discuss: Hacker News
🏛️Software Architecture Patterns
Flag this post
I Taught an AI to Dream
blog.minibase.ai·6h·
Discuss: Hacker News
🏛️Software Architecture Patterns
Flag this post
Show HN: Oodle – Unified Debugging with OpenSearch and Grafana
blog.oodle.ai·7h·
Discuss: Hacker News
🏛️Software Architecture Patterns
Flag this post
Open Source Context-Aware PII Classifier
corp.roblox.com·3h·
Discuss: Hacker News
High Performance Computing
Flag this post
Windsurf Codemaps: Understand Code, Before You Vibe It
cognition.ai·5h·
⚙️DevOps Practices
Flag this post
Ranking LLMs based on 180k French votes (French government's AI arena)
comparia.beta.gouv.fr·10h·
Discuss: Hacker News
🏛️Software Architecture Patterns
Flag this post
How We Built a Custom Vision LLM to Improve Document Processing at Grab
engineering.grab.com·23h·
Discuss: Hacker News
High Performance Computing
Flag this post
Most Gen AI Players Remain 'Far Away' from Profiting: Interview with Andy Wu
library.hbs.edu·3h·
Discuss: Hacker News
High Performance Computing
Flag this post