benocodes's submissions

1.		The Greenland Ice Sheet is fracturing faster than expected (nature.com)
		9 points by benocodes 6 days ago \| past \| 1 comment
2.		Solving key challenges in AI-assisted code reviews (qodo.ai)
		16 points by benocodes 14 days ago \| past \| 1 comment
3.		Considerations for making a tree view component accessible (github.blog)
		1 point by benocodes 18 days ago \| past
4.		Cloud Efficiency at Netflix (netflixtechblog.com)
		46 points by benocodes 45 days ago \| past \| 52 comments
5.		Introducing Configurable Metaflow (netflixtechblog.com)
		1 point by benocodes 45 days ago \| past
6.		How Will We Know We're Not Alone? (quantamagazine.org)
		4 points by benocodes 46 days ago \| past
7.		How close is AI to human-level intelligence? (nature.com)
		1 point by benocodes 75 days ago \| past
8.		Model Context Protocol (anthropic.com)
		872 points by benocodes 83 days ago \| past \| 258 comments
9.		Exploring Gen AI: Copilot's new multi-file editing (martinfowler.com)
		1 point by benocodes 86 days ago \| past
10.		Dental evidence for extended growth in early Homo from Dmanisi (nature.com)
		2 points by benocodes 3 months ago \| past
11.		Netflix's Distributed Counter Abstraction (netflixtechblog.com)
		133 points by benocodes 3 months ago \| past \| 71 comments
12.		Debate May Help AI Models Converge on Truth (quantamagazine.org)
		3 points by benocodes 3 months ago \| past
13.		Vision Language Models Are In-Context Value Learners (generative-value-learning.github.io)
		1 point by benocodes 3 months ago \| past
14.		There Are Three Types of Twilight (scientificamerican.com)
		2 points by benocodes 3 months ago \| past \| 1 comment
15.		How the Brain Summons Deep Sleep to Speed Healing (scientificamerican.com)
		4 points by benocodes 3 months ago \| past \| 1 comment
16.		Gene-editing tool will help the world cope with climate change (technologyreview.com)
		2 points by benocodes 3 months ago \| past
17.		Support for Claude Sonnet 3.5, OpenAI O1 and Gemini 1.5 Pro (qodo.ai)
		69 points by benocodes 3 months ago \| past \| 35 comments
18.		Chain-of-thought can hurt performance on tasks where thinking makes humans worse (arxiv.org)
		371 points by benocodes 3 months ago \| past \| 250 comments
19.		LLMs know more than they show: On the intrinsic representation of hallucinations (arxiv.org)
		137 points by benocodes 3 months ago \| past \| 140 comments
20.		Custom LLM as a Judge to Detect Hallucinations with Braintrust (cookbook.openai.com)
		1 point by benocodes 3 months ago \| past
21.		Improving Conversational AI at Airbnb (medium.com/airbnb-engineering)
		1 point by benocodes 3 months ago \| past
22.		Agents Thinking Fast and Slow: A Talker-Reasoner Architecture (arxiv.org)
		9 points by benocodes 3 months ago \| past
23.		Sparse Crosscoders for Cross-Layer Features and Model Diffing (transformer-circuits.pub)
		2 points by benocodes 3 months ago \| past
24.		Getting Claude Computer Use agent to spin up another agent in its VM (twitter.com/gavriel_cohen)
		4 points by benocodes 3 months ago \| past
25.		OpenAI's approach to AI and national security (openai.com)
		2 points by benocodes 3 months ago \| past
26.		OpenAI scientist: '20 seconds of thinking worth 100,000x more data' (venturebeat.com)
		3 points by benocodes 3 months ago \| past
27.		Claude Computer Use agent spins up another agent in its VM (twitter.com/gavriel_cohen)
		1 point by benocodes 3 months ago \| past
28.		Drasi: Microsoft's open source data processing platform for event-driven systems (github.com/drasi-project)
		331 points by benocodes 3 months ago \| past \| 67 comments
29.		How Uber Optimizes LLM Training (uber.com)
		1 point by benocodes 3 months ago \| past
30.		Solving complex problems with OpenAI o1 models (openai.com)
		6 points by benocodes 3 months ago \| past \| 1 comment
		More