🔄 MLOps - queenrose54 · Scour

Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora 📏LLM Evaluation

The Data Layer Tax for Robot Learning 📏LLM Evaluation

rerun.io·15h·Hacker News

Monitoring LLM behavior: Drift, retries, and refusal patterns 📏LLM Evaluation

venturebeat.com·5d·Hacker News

Continually improving our agent harness 📏LLM Evaluation

cursor.com·15h

[AINews] The Inference Inflection 📈Prometheus

·1d

LLM Quantization ⛓️Langchain

huggingface.co·3h·Hacker News

An Empirical Study of Methods for SFTing Opaque Reasoning Models 📏LLM Evaluation

lesswrong.com·6d

The Inference Economy: Token Use 📏LLM Evaluation

frontierai.substack.com·9h·Substack

Adaptive Thinking: Large Language Models Know When to Think in Latent Space 📏LLM Evaluation

machinelearning.apple.com·2d

Our evaluation of OpenAI’s GPT-5.5 cyber capabilities 📏LLM Evaluation

simonwillison.net·4h

AI Infrastructure Architect · Builder · Author 📏LLM Evaluation

markferraz.com·9h·Hacker News

Flow generation through natural language: An agentic modeling approach (11 minute read) 📏LLM Evaluation

shopify.engineering·1d

DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles 🧠DeepSeek

lmsys.org·5d·Hacker News

GoogleCloudPlatform/activation-model-scanner: Verify language model safety before deployment by analyzing activation patterns 📏LLM Evaluation

github.com·23h·Hacker News

Three Cobblers, One Zhuge Liang: Making Cheaper Models Work Together 📏LLM Evaluation

markhuang.ai·1d·Hacker News

not much happened today 📈Prometheus

news.smol.ai·22h

Prometheus-based Grafana Server Monitoring ｜ fernvenue's Blog 📈Prometheus

blog.fernvenue.com·4h

Featherless.ai pulls in $20M to scale serverless hosting for open-source AI models 🚢Kubernetes

siliconangle.com·4h

OpenShift AI observability summarizer: Transform metrics into meaning 📈Prometheus

developers.redhat.com·3d

PEAKS No 42: The Open-Weight Uprising: GPT-5.5, Qwen Beats a 397B Giant, and Your Jira Data Is Now AI Training Fuel 📈Prometheus

bogdandeac.com·2d

Log in to enable infinite scrolling