惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
MongoDB | Blog
MongoDB | Blog
博客园_首页
博客园 - 三生石上(FineUI控件)
博客园 - 聂微东
B
Blog RSS Feed
D
Docker
IT之家
IT之家
大猫的无限游戏
大猫的无限游戏
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
阮一峰的网络日志
阮一峰的网络日志
罗磊的独立博客
Recent Announcements
Recent Announcements
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
A
About on SuperTechFans
The GitHub Blog
The GitHub Blog
G
Google Developers Blog
V
V2EX
量子位
雷峰网
雷峰网
月光博客
月光博客
云风的 BLOG
云风的 BLOG
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
T
Tailwind CSS Blog

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace
The LLM Death Spiral | Hacker News
robomartin · 2026-05-22 · via Hacker News - Newest: "LLM"

Over the last year and a half I have witnessed something that is truly alarming. I am calling it "The LLM Death Spiral".

This is the case of two people at a company using LLM's extensively for email communications. Over time, the LLM being used by the Boss, has been tuned to interpret emails from the Worker, as being negative, aggressive, inappropriate, etc.

I should add that, before LLM's the Boss was not a writer or reader. In other words, not great at creating or reading written communications. As a result, as soon as LLM's entered the picture, the Boss jumped in head-first and every single email the Boss writes is visibly created by an LLM.

The Death Spiral refers to this effect whereby this situation, through a negative feedback loop, degrades over time. Every Worker email is interpreted in an increasingly negative light, no matter how carefully crafted it might be. The situation got so bad that the Worker got written-up and threatened with firing.

This almost became a perfect embodiment of Plato's Allegory of the Cave. The Boss was, after a few iterations, only seeing the shadows on the wall cast by the LLM effectively trained by the Boss through interaction.

I wonder how much of this might be going on in this brave new paradigm, with the potential of LLM's truly damaging human relations and by, effectively, largely removing the human factor from communications.