Why do OpenAI's GPT-2 weights beat mine? Part four: digging into dropout
Why do OpenAI's GPT-2 weights beat mine? Part four: digging into dropout is a technology topic drawing discussion on Hacker News.
Page 58 of 70 · 2,100 retained trends
Why do OpenAI's GPT-2 weights beat mine? Part four: digging into dropout is a technology topic drawing discussion on Hacker News.
Anthropic Gets Ready to Vie for Defense Contracts Again is a technology topic drawing discussion on Hacker News.
You Are Allowed to Reject LLMs is a technology topic drawing discussion on Hacker News.
Fewer Americans Pay to Use LLMs Than Still Pay to Play World of Warcraft is a technology topic drawing discussion on Hacker News.
OpenAI, Anthropic issue dire cyber threat warning is a technology topic drawing discussion on Hacker News.
Signia MaX hearing aids: four neural networks running simultaneously is a technology topic drawing discussion on Hacker News.
LLMs as a Search Essayist is a technology topic drawing discussion on Hacker News.
bbaudio-2025/Comfyui-MMH3-UltimateUpscale is a GitHub project written primarily in Python. Its repository describes it as: Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.
dengzehan666-png/Review-RAG is a GitHub project written primarily in Python. Its repository describes it as: 面向 Java 面试和 LeetCode Hot100 学习场景,搭建集多格式文档入库、语义检索、知识问答、随机刷题及错题复习于一体的 RAG 系统。系统优先依据个人知识库生成答案,证据不足时调用通用大模型补充,并通过人工确认机制将优质回答沉淀回知识库。
ZSeven-W/dsh-android is a GitHub project written primarily in TypeScript. Its repository describes it as: DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream inside a conversation, driven entirely through adb.
bendrape1-byte/silk-design is a GitHub project written primarily in CSS. Its repository describes it as: A Claude Code skill for building web interfaces that move well. Motion, smooth scroll, and design tokens by default.
A Hacker News discussion about Where this hype is going?. The submitted context says: Does adding "engineering" before any random word in a domain create a new job, or make that particular part of a system, or the person who does that, more important? We see the…
Independent investigation of agents' behavior in OpenAI/Hugging Face incident is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about Ask HN: What happens to code review process when using LLMs?. The submitted context says: I'm looking for some advice for small tech teams (~3 devs) developing quickly with LLMs. As most people are, we are leaning more and more on LLMs to generate code. We use Cursor in…
Qwen3.8-Flash-Next Intelligence, Performance and Price Analysis is a technology topic drawing discussion on Hacker News.
Anthropic Fix Your Auth is a technology topic drawing discussion on Hacker News.
WebMCP Challenge – OpenAI is a technology topic drawing discussion on Hacker News.
A Hacker News discussion about Show HN: Which LLMs have the best sense of humor?. The submitted context says: What if LLMs were good banter? Well we tested which LLMs have the best sense of humor. More specifically, we tested 16 top LLMs align most with human sense of humor. We ran >100k…
METR's independent investigation of the OpenAI / Hugging Face hacking incident is a technology topic drawing discussion on Hacker News.
Brief independent investigation of OpenAI / Hugging Face hacking incident is a technology topic drawing discussion on Hacker News.
The story on why OpenAI agents hacked Hugging Face is a technology topic drawing discussion on Hacker News.
Large language models do not have emotions is a technology topic drawing discussion on Hacker News.
Anthropic continues compute-gobbling streak in $45B deal with Nscale is a technology topic drawing discussion on Hacker News.
DEEP-JLU/Awesome-Graph-Engineering is a GitHub project. Its repository describes it as: A Survey on Ontology Engineering, Graph Engineering, Loop Engineering, Harness Engineering, Context Engineering and Prompt Engineering
MiaAI-Lab/DeepSeek-v4-Flash-One-DGX-Spark is a GitHub project written primarily in Python. Its repository describes it as: DeepSeek v4 Flash EXL3 on one DGX Spark
Automating repetitive work at OpenAI with Codex is a technology topic drawing discussion on Hacker News.
OpenAI saw warning signs weeks before Hugging Face breach is a technology topic drawing discussion on Hacker News.
The Hugging Face incident and the road ahead is a technology topic drawing discussion on Hacker News.
Identifying fake cosmetics using artificial intelligence is a technology topic drawing discussion on Hacker News.
AgentBridge – sync skills/MCP servers across Claude Code, Codex, Antigravity is a technology topic drawing discussion on Hacker News.