JnBrymn's submissions

1.		Emergent Hierarchical Reasoning in LLMs Through Reinforcement Learning (arxiv.org)
		5 points by JnBrymn 5 hours ago \| past \| discuss
2.		Not a Bubble (twitter.com/speculator_io)
		3 points by JnBrymn 5 hours ago \| past \| discuss
3.		How to Become a Mechanistic Interpretability Researcher – LessWrong (lesswrong.com)
		2 points by JnBrymn 12 days ago \| past \| discuss
4.		Don't Build Multi-Agents (cognition.ai)
		123 points by JnBrymn 14 days ago \| past \| 89 comments
5.		The Bitter Lesson Is Misunderstood (obviouslywrong.substack.com)
		367 points by JnBrymn 18 days ago \| past \| 251 comments
6.		Fine-tuning LLM Agents without Fine-tuning LLMs (github.com/agent-on-the-fly)
		2 points by JnBrymn 20 days ago \| past
7.		We must build AI for people; not to be a person (mustafa-suleyman.ai)
		4 points by JnBrymn 26 days ago \| past \| 1 comment
8.		Yuck. Anthropic welcomes dystopia by hinting that AI should have moral status (twitter.com/jnbrymn)
		21 points by JnBrymn 27 days ago \| past \| 24 comments
9.		The Brain's Ability to Process Stereo Sound · Thought Box (jnbrymn.com)
		4 points by JnBrymn 29 days ago \| past
10.		You, Your Tools, and Your Team of AI Agents – By Owen Zanzal (medium.com/devops-ai)
		1 point by JnBrymn 46 days ago \| past
11.		Symposium Driven Development: A Not So New Paradigm for Software Creation (medium.com/devops-ai)
		1 point by JnBrymn 46 days ago \| past \| 1 comment
12.		Learning without training: The implicit dynamics of in-context learning (arxiv.org)
		2 points by JnBrymn 49 days ago \| past
13.		Flavors of NDCG – Normalized to What? (softwaredoug.com)
		2 points by JnBrymn 53 days ago \| past
14.		Winning the Race: America's AI Action Plan [pdf] (whitehouse.gov)
		1 point by JnBrymn 53 days ago \| past \| 1 comment
15.		Fine-Tuning in Sentence Transformers 3 – Aurelio AI (aurelio.ai)
		1 point by JnBrymn 54 days ago \| past
16.		Conversational image segmentation with Gemini 2.5 Blog (googleblog.com)
		5 points by JnBrymn 54 days ago \| past
17.		Towards Autonomous Micromobility Through Scalable Urban Simulation (github.com/metadriverse)
		3 points by JnBrymn 64 days ago \| past
18.		Grok 4 is now the leading AI model ( ArtificialAnlys) (twitter.com/artificialanlys)
		13 points by JnBrymn 67 days ago \| past \| 6 comments
19.		Pliny the Liberator 󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾: Here's the new Grok 4 system prompt (twitter.com/elder_plinius)
		10 points by JnBrymn 67 days ago \| past \| 5 comments
20.		A Survey on Latent Reasoning (huggingface.co)
		2 points by JnBrymn 67 days ago \| past
21.		Context Engineering (langchain.com)
		2 points by JnBrymn 71 days ago \| past
22.		Gemini CLI (simonwillison.net)
		5 points by JnBrymn 81 days ago \| past
23.		Reinforcement learning, explained with a minimum of math and jargon (understandingai.org)
		192 points by JnBrymn 83 days ago \| past \| 12 comments
24.		AbsenceBench: Language models can't tell what's missing (arxiv.org)
		324 points by JnBrymn 86 days ago \| past \| 84 comments
25.		Recipes – A Pattern for Common Code Transformations (arcturus-labs.com)
		2 points by JnBrymn 88 days ago \| past
26.		Beyond Code-Centric: Agents Code but the Problem of Clear Specification Remains (gregceccarelli.com)
		4 points by JnBrymn 88 days ago \| past
27.		Shade-Arena: Evaluating Sabotage and Monitoring in LLM Agents [pdf] (anthropic.com)
		4 points by JnBrymn 88 days ago \| past
28.		Recipes – A Vibe Coding Pattern for Common Code Transformations (arcturus-labs.com)
		2 points by JnBrymn 89 days ago \| past
29.		Don't Build Multi-Agents (cognition.ai)
		5 points by JnBrymn 3 months ago \| past
30.		Takeaways from AI Engineer Fair: The startup playbook is being rewritten (geekwire.com)
		2 points by JnBrymn 3 months ago \| past
		More