Hacker Newsnew | past | comments | ask | show | jobs | submit | JnBrymn's submissionslogin
1.
Why Spec-Driven Development Breaks at Scale (and How to Fix It) – Arcturus Labs (arcturus-labs.com)
1 point by JnBrymn 1 day ago | past | discuss
2.
Understanding neural networks through sparse circuits – OpenAI (openai.com)
1 point by JnBrymn 12 days ago | past | discuss
3.
GPT-5.1 Prompting Guide (cookbook.openai.com)
4 points by JnBrymn 14 days ago | past
4.
Context Engineering Requires AI Empathy – Arcturus Labs (arcturus-labs.com)
1 point by JnBrymn 20 days ago | past
5.
Spec-Driven Development: things you need to know about specs – AI Native Dev (ainativedev.io)
2 points by JnBrymn 26 days ago | past
6.
Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity (arxiv.org)
1 point by JnBrymn 27 days ago | past
7.
Can We Fix Social Media? Testing Prosocial Interventions Using Social Simulation (arxiv.org)
2 points by JnBrymn 35 days ago | past
8.
Fire Yourself First: The E-Myth Approach to Iteratively AI App Development (arcturus-labs.com)
2 points by JnBrymn 38 days ago | past
9.
Why Spec-Driven Development Breaks at Scale (and How to Fix It) – Arcturus Labs (arcturus-labs.com)
2 points by JnBrymn 38 days ago | past
10.
Context engineering is sleeping on the humble hyperlink • mbleigh.dev (mbleigh.dev)
1 point by JnBrymn 38 days ago | past
11.
Karpathy on DeepSeek-OCR paper: Are pixels better inputs to LLMs than text? (twitter.com/karpathy)
410 points by JnBrymn 41 days ago | past | 173 comments
12.
An alignment auditing agent capable of quickly exploring alignment hypothesis (github.com/safety-research)
2 points by JnBrymn 46 days ago | past
13.
Agentic Context Engineering: Evolving Contexts for SelfImproving Language Models (arxiv.org)
2 points by JnBrymn 51 days ago | past
14.
Agentic Context Engineering: Evolving Contexts for SelfImproving Language Models (arxiv.org)
2 points by JnBrymn 54 days ago | past
15.
Reasoning boosts search relevance 15-30% (softwaredoug.com)
3 points by JnBrymn 56 days ago | past
16.
Petri: An open-source auditing tool to accelerate AI safety research \ Anthropic (anthropic.com)
2 points by JnBrymn 56 days ago | past
17.
Embracing the parallel coding agent lifestyle (simonw.substack.com)
2 points by JnBrymn 56 days ago | past
18.
Levels of AI agent autonomy: learning from self-driving cars – AI Native Dev (ainativedev.io)
2 points by JnBrymn 59 days ago | past
19.
Sycophantic AI increases attitude extremity and overconfidence (osf.io)
2 points by JnBrymn 60 days ago | past
20.
Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe (arxiv.org)
1 point by JnBrymn 67 days ago | past
21.
PsyArXiv Preprints – Quantifying Human-AI Synergy (osf.io)
2 points by JnBrymn 67 days ago | past
22.
Things in the "Context Plane" – By Shagility (agiledata.substack.com)
1 point by JnBrymn 69 days ago | past
23.
AI companion futures osmarks' website (osmarks.net)
1 point by JnBrymn 75 days ago | past
24.
The scapegoats guide to organizational 'transformation' (softwaredoug.com)
3 points by JnBrymn 76 days ago | past
25.
Scaling AI Evaluation Through Expertise (harvey.ai)
2 points by JnBrymn 76 days ago | past
26.
Julia Neagu: Why evals haven't landed (yet) + lessons from evals at Copilot (twitter.com/juliaaneagu)
4 points by JnBrymn 76 days ago | past
27.
Emergent Hierarchical Reasoning in LLMs Through Reinforcement Learning (arxiv.org)
5 points by JnBrymn 77 days ago | past
28.
Not a Bubble (twitter.com/speculator_io)
3 points by JnBrymn 77 days ago | past
29.
How to Become a Mechanistic Interpretability Researcher – LessWrong (lesswrong.com)
2 points by JnBrymn 89 days ago | past
30.
Don't Build Multi-Agents (cognition.ai)
123 points by JnBrymn 3 months ago | past | 89 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: