A Null Pointer Exception Brought Down Mighty Google;7 Hours of Downtime
getpanto.ai·12h·
Discuss: Hacker News
⌨️Prompt Engineering
How I build software quickly
evanhahn.com·2d·
Discuss: Lobsters, Hacker News, Hacker News
⌨️Prompt Engineering
Show HN: Custom AI tool chains you can self-host or scale to the cloud
brofty.com·1d·
Discuss: Hacker News
🏡Local running LLMs
Model Cards Revisited: Bridging the Gap Between Theory and Practice for Ethical AI Requirements
arxiv.org·1d
🏡Local running LLMs
What can agents actually do?
lethain.com·3d·
Discuss: Lobsters, Hacker News
🏡Local running LLMs
A Probabilistic Approach to Uncertainty Quantification Leveraging 3D Geometry
arxiv.org·5h
🤖AI
Controlling Thinking Speed in Reasoning Models
arxiv.org·2d
🏡Local running LLMs
Prompt Migration: Stabilizing GenAI Applications with Evolving Large Language Models
arxiv.org·1d
⌨️Prompt Engineering
On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification
arxiv.org·1d
🤖AI
Junior Roles Aren't Going Away
iamcharliegraham.substack.com·1d·
Discuss: Substack
🤖AI
An autonomous agent for auditing and improving the reliability of clinical AI models
arxiv.org·1d
🤖AI
Domain adaptation of large language models for geotechnical applications
arxiv.org·1d
🏡Local running LLMs
Evaluating AI Counseling in Japanese: Counselor, Client, and Evaluator Roles Assessed by Motivational Interviewing Criteria
arxiv.org·2d
⌨️Prompt Engineering
Designing Robust Software Sensors for Nonlinear Systems via Neural Networks and Adaptive Sliding Mode Control
arxiv.org·5h
🏡Local running LLMs
GTA1: GUI Test-time Scaling Agent
arxiv.org·1d
⌨️Prompt Engineering
IMPACT: Industrial Machine Perception via Acoustic Cognitive Transformer
arxiv.org·5h
⌨️Prompt Engineering
VisioPath: Vision-Language Enhanced Model Predictive Control for Safe Autonomous Navigation in Mixed Traffic
arxiv.org·5h
🏡Local running LLMs
Hidden Prompts in Manuscripts Exploit AI-Assisted Peer Review
arxiv.org·1d
⌨️Prompt Engineering
Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving
arxiv.org·5h
🏡Local running LLMs
Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models
arxiv.org·5h
⌨️Prompt Engineering