mustaphah's submissions

1.		Tell HN: Claude two rate limits don't know about each other
		2 points by mustaphah 26 days ago \| past
2.		Enhancing gut-brain communication reversed cognitive decline in aging mice (stanford.edu)
		386 points by mustaphah 27 days ago \| past \| 185 comments
3.		Many SWE-bench-Passing PRs would not be merged (metr.org)
		278 points by mustaphah 28 days ago \| past \| 154 comments
4.		AGI is an unscientific myth (tandfonline.com)
		4 points by mustaphah 41 days ago \| past \| 2 comments
5.		Web Verbs (github.com/nlweb-ai)
		1 point by mustaphah 45 days ago \| past
6.		OpenAI's 5-month experiment: building a product with no human-written code (openai.com)
		2 points by mustaphah 49 days ago \| past
7.		SkillsBench: Benchmarking how well agent skills work across diverse tasks (arxiv.org)
		364 points by mustaphah 51 days ago \| past \| 171 comments
8.		Evaluating AGENTS.md: are they helpful for coding agents? (arxiv.org)
		232 points by mustaphah 51 days ago \| past \| 161 comments
9.		Curosr: Expanding our long-running agents research preview (cursor.com)
		3 points by mustaphah 53 days ago \| past
10.		Measuring Time Horizon Using Claude Code and Codex (metr.org)
		1 point by mustaphah 53 days ago \| past
11.		SWE-ContextBench: context learning benchmark in coding (arxiv.org)
		1 point by mustaphah 54 days ago \| past
12.		SWE-AGI: benchmarking spec-driven software construction (arxiv.org)
		1 point by mustaphah 55 days ago \| past \| 1 comment
13.		Code Formatting Silently Consumes Your LLM Budget (arxiv.org)
		1 point by mustaphah 58 days ago \| past
14.		Agent Trace by Cursor: open spec for tracking AI-generated code (agent-trace.dev)
		1 point by mustaphah 67 days ago \| past
15.		METR releases Time Horizon 1.1 with 34% more tasks (metr.org)
		1 point by mustaphah 68 days ago \| past
16.		Coffee timing isn't one-size-fits-all (examine.com)
		4 points by mustaphah 69 days ago \| past
17.		ChatGPT subscription support in Kilo Code (kilo.ai)
		1 point by mustaphah 72 days ago \| past
18.		Imposter Syndrome Predicts Perfectionism (psypost.org)
		2 points by mustaphah 73 days ago \| past
19.		Motivation acts as a camera lens that shapes how memories form (psypost.org)
		2 points by mustaphah 73 days ago \| past
20.		Claude Code: Merging Slash Commands into Skills (x.com)
		2 points by mustaphah 73 days ago \| past \| 2 comments
21.		The visual feedback tool for coding agents (agentation.dev)
		2 points by mustaphah 75 days ago \| past
22.		Agent Skills to help developers using AI agents with Supabase (github.com/supabase)
		1 point by mustaphah 75 days ago \| past
23.		METR AI Benchmark: Clarifying Limitations of Time Horizon (metr.org)
		2 points by mustaphah 75 days ago \| past
24.		Scaling PostgreSQL to power 800M ChatGPT users (openai.com)
		348 points by mustaphah 76 days ago \| past \| 136 comments
25.		Claude Code plugin that rings your phone when a run needs you (github.com/zeframlou)
		2 points by mustaphah 84 days ago \| past \| 1 comment
26.		Exercise can be nearly as effective as therapy for depression (sciencedaily.com)
		402 points by mustaphah 89 days ago \| past \| 393 comments
27.		Party of One for Code Review (tidyfirst.substack.com)
		2 points by mustaphah 3 months ago \| past
28.		FrontierScience Benchmark by OpenAI (openai.com)
		17 points by mustaphah 3 months ago \| past \| 1 comment
29.		Open Scouts: AI-driven web monitoring (firecrawl.dev)
		1 point by mustaphah 3 months ago \| past
30.		A Rosetta Stone for AI Benchmarks (epoch.ai)
		2 points by mustaphah 4 months ago \| past
		More