✅ evals - zhuangda · Scour

AI agents are only as useful as the tools they can safely touch ✍️Prompt Engineering

blog.jenuel.dev·1d·DEV

Google opens TPUs to enterprises beyond its own cloud via Blackstone JV 🦆DuckDB

networkworld.com·1d

AI researchers push reliability tests for agent systems ✍️Prompt Engineering

kite.kagi.com·4d

Synthesis and Evaluation of Long-term History-aware Medical Dialogue ✍️Prompt Engineering

Show HN: Pokémon SVG Generation LLM Benchmark 🤖AI

svg-bench.fenx.work·6d·Hacker News

Presentation: Powering the Future: Building Your GenAI Infrastructure Stack ✍️Prompt Engineering

·1d

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality ✍️Prompt Engineering

huggingface.co·6d

Tetrahedroned/Agent-Braille: Deterministic 8-bit machine-to-machine protocol for AI agent state. ~92% fewer state-tracking tokens on real Claude Code sessions, a proven single-bit-error-safe command code, fully reproducible. ✍️Prompt Engineering

github.com·2d·Hacker News

Why Code DSLs Will Replace JSON Tool Calling ✍️Prompt Engineering

mukulsingh105.github.io·6d·Hacker News

FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale ✍️Prompt Engineering

frontier-cs.org·5d·Hacker News

Creating “Chain of Evidence” (CoE) Content for GEO ✍️Prompt Engineering

Anthropic commits $200M with Gates Foundation to deploy AI in global health, education, and agriculture 🤖AI

thenextweb.com·5d

Build petabyte-scale synthetic test data with Amazon EMR on EC2 🦆DuckDB

aws.amazon.com·1d

Auditing Multimodal LLM Raters: Central Tendency Bias in Clinical Ordinal Scoring ✍️Prompt Engineering

Image-To-Video Tricks Every Creator Should Know ✍️Prompt Engineering

·4d

Deep Learning Weekly: Issue 455 ✍️Prompt Engineering

deeplearningweekly.com·6d

What Is AI Jailbreaking? A Beginner's Guide to the Cat-and-Mouse Game Behind Every Chatbot ✍️Prompt Engineering

Your AI Agent Works Perfectly in the Demo. Here Are the 6 Ways It Dies in Production. ✍️Prompt Engineering

towardsai.net·1d

Feed Your Data Lake With Real-Time, Analytics-Ready Tables for 30-50% Lower Cost Using Tableflow 🦆DuckDB

confluent.io·6d

Fine-Tuning Often Makes Your AI Model Worse ✍️Prompt Engineering

siliconopera.com·4d

Sign up or log in to see more results

Log in to enable infinite scrolling