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

The Cloudflare Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
人人都是产品经理
人人都是产品经理
C
Check Point Blog
有赞技术团队
有赞技术团队
H
Help Net Security
V
Vulnerabilities – Threatpost
N
News | PayPal Newsroom
Hacker News - Newest:
Hacker News - Newest: "LLM"
L
LINUX DO - 最新话题
Apple Machine Learning Research
Apple Machine Learning Research
博客园 - 【当耐特】
爱范儿
爱范儿
I
InfoQ
V
Visual Studio Blog
O
OpenAI News
Google DeepMind News
Google DeepMind News
S
Security Affairs
T
Troy Hunt's Blog
P
Palo Alto Networks Blog
Spread Privacy
Spread Privacy
Engineering at Meta
Engineering at Meta
雷峰网
雷峰网
N
Netflix TechBlog - Medium
Latest news
Latest news
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Webroot Blog
Webroot Blog
S
Schneier on Security
MongoDB | Blog
MongoDB | Blog
T
Tor Project blog
V2EX - 技术
V2EX - 技术
Security Latest
Security Latest
Cloudbric
Cloudbric
The GitHub Blog
The GitHub Blog
酷 壳 – CoolShell
酷 壳 – CoolShell
B
Blog RSS Feed
C
CERT Recently Published Vulnerability Notes
T
The Exploit Database - CXSecurity.com
P
Privacy International News Feed
S
Securelist
C
Cisco Blogs
博客园_首页
TaoSecurity Blog
TaoSecurity Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Security Archives - TechRepublic
Security Archives - TechRepublic
P
Proofpoint News Feed
K
KPMG report finds enterprise disconnect between AI and its ROI | CIO
T
Threat Research - Cisco Blogs
阮一峰的网络日志
阮一峰的网络日志
S
Secure Thoughts

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 - AronDaron/dataset-generator: No-code desktop app for generating high-quality synthetic datasets to fine-tune LLMs — plan-then-execute pipeline, LLM-as-judge, HuggingFace upload. 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 GitHub - Nyquest-ai/nyquest-rust-fullstack-pub: Nyquest — Semantic Compression Proxy for LLMs. 350+ rules, local LLM stage, 15-75% token savings. Full Rust stack. GitHub - TheoV823/mneme: Enforce architectural decisions in AI-assisted development. GitHub - klemenvod/TokenBrawl: A 1v1 Bomberman-style game where two LLM agents play autonomously against each other. No human plays — you watch the AIs fight. Each agent receives a text description of the board state, reasons about it, and outputs a move as JSON. The game engine executes it. Introducing the Common AI Provider: LLM and AI Agent Support for Apache Airflow Power Circuit AI: Designing Power Electronic Circuits for Motor Drives with Generative Artificial Intelligence Ask HN: How to program with IDE and LLM on CPU locally? Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis Bonsai 1-bit WebGPU - a Hugging Face Space by webml-community The LLM Fallacy: Misattribution in AI-Assisted Cognitive Workflows Ask HN: Simple tooling for local LLM code critique without IDE integration? Can a General LLM Diagnose a DICOM Slice? A 10-Case Public Benchmark Charts-of-Thought: Enhancing LLM Visualization Literacy (PDF, 2026) GitHub - Mesh-LLM/mesh-llm: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. GitHub - seamus-brady/springdrift: A persistent runtime for long-lived LLM agents Writing an LLM from scratch, part 32k -- Interventions: training a better model locally with gradient accumulation Ask HN: Which LLM model and agentic CLI are you using for local development? GitHub - wayneColt/modelcascade: Route local. Escalate smart. Never overspend. Open-source multi-model cascade routing for autonomous agents. LLM pricing is 100x harder than you think GitHub - asakin/llm-primer: Pre-warmed Claude Code sessions in tmux. No startup wait. GitHub - EggerMarc/chat-rs: A multi-provider LLM framework for Rust. GitHub - SynapseKit/SynapseKit: Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS. A Claude Skill that Makes LLM Paragraphs More Bearable Does Gas Town 'steal' usage from users' LLM credits & paid services to improve itself? What's Claude Code Actually Doing? Open the Black Box with the Arthur Engine Milla Jovovich's New Open Source LLM Memory App and the Dark Code Problem Your intuition of LLM token usage might be wrong Show HN: Bloomberg Terminal for LLM ops – free and open source GitHub - 0xchamin/mcptube: Transform YouTube videos into a compounding knowledge base with transcripts, vision analysis, and agentic search. Works as an MCP server for Claude, Copilot & more. Show HN: Open KB: Open LLM Knowledge Base Your LLM is a compiler, not a runtime GitHub - sapountzis/Unslop: A Web Feed That Deserves You crates.io: Rust Package Registry Beyond Karpathy's LLM-Wiki: The Necessity of Cognitive Governance GitHub - amitshekhariitbhu/llm-internals: Learn LLM internals step by step - from tokenization to attention to inference optimization. GitHub - parallem-ai/parallem: An expressive library for running agents with the Batch API. GitHub - stfurkan/pi-llm LLM-Wiki Show HN: Formal – Formal verification for AI-generated code using Lean 4 LRTS – Regression testing for LLM prompts (open source, local-first) LLM Wiki Skill: Build a Second Brain with Claude Code and Obsidian I built an LLM Wiki and RAG solution: here's a demo for a security KB The biggest advance in AI since the LLM Predict-Rlm: The LLM Runtime That Lets Models Write Their Own Control Flow the-synthetic-library/the-synthetic-mind at main · joshferrer1/the-synthetic-library GitHub - yisding/reviewwiggum GitHub - Donnyb369/mcp-spine: Context Minifier & State Guard — Local-first MCP middleware proxy GitHub - Beledarian/wgpu-llm: A from-scratch LLM inference engine that uses wgpu (the cross-platform WebGPU implementation) to dispatch WGSL compute shaders for every math operation a Transformer needs. No CUDA. No Python. No massive framework dependencies. Just Rust, raw shaders, and your GPU. GitHub - anitiue/Hindsight: An experience-driven self-improvement framework for LLM agents — 基于经验的 LLM Agent 自我改进框架 GitHub - stef41/lmscan: 🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline. GitHub - alainnothere/AmdPerformanceTesting: Amd Performance Testing Ask HN: Is a purely Markdown-based CRM a terrible idea? Optimized for LLM agents Context Engineering - LLM Memory and Retrieval for AI Agents | Weaviate little_helper_tui/letter.md at main · sleepyeldrazi/little_helper_tui GitHub - EvanZhouDev/umr: The Unified Model Registry for all your local AI apps. GitHub - JordanCT/VigIA-Orchestrator Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain A Taxonomy of RL Environments for LLM Agents Llama LLM Network Feture GitHub - genedeng-ca/ai-mac-migration: AI-powered Mac-to-Mac migration tool - replace Apple Migration Assistant with intelligent, selective transfer using local LLMs GitHub - lunargate-ai/gateway: High-performance self-hosted AI gateway (OpenAI-compatible) with routing, retries, and streaming GitHub - AuthBits/webmcp: A lightweight, prompt-driven MCP web research server for high-quality LLM powered information extraction. Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Springdrift: An Auditable Persistent Runtime for LLM Agents with Case-Based Memory, Normative Safety, and Ambient Self-Perception High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization TIDE: Token-Informed Depth Execution for Per-Token Early Exit in LLM Inference Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
A comfortable slow boil
maxime_ · 2026-06-19 · via Hacker News - Newest: "LLM"

Lately I’ve been reading a lot about burnout in the age of AI and somewhat been recognising the symptoms : the FOMO ("I could be building stuff right now"), the brain that doesn’t turn off, the context switching pushed to its maximum that makes evenings feel like a slow re-entry (when I haven’t had any issue with leaving work at the door for a good 8 years) and I am still hesitant to call what I’m living burnout.

The campsite, not the fire

I keep noticing people around me look at the last 12-18 months and say oh god there’s a fire, someone put it out. I see the fire too, but from where I’m standing it looks less like a forest going up and more like a campsite I used to go to a lot in my 20s, at least for now.

I think that for someone who had a stable, well-defined identity at work (or at least as much define as it can be), the disruption is existential and it feels to them like the ground under their feet is on fire, not the firewood. I see that especially in colleagues who never really had to delegate that much before, and who built a sense of accomplishment around being the one who wrote and shipped the thing. Watching an agent draft what you used to draft when your identity is the drafting, is the fire. I happen to have made peace with delegation earlier in my career (with actual humans, not agents of course) and so the same flames hit different.

Maybe I’m in a flow state, or maybe I’m in a hot bath at the stage where the bath still feels nice and I haven’t noticed the temperature rising.

The boreout I’m climbing out of

The year before this one was a bumpy one for me professionally (the kind that made me feel like I no longer belonged in the place where I worked) and by the end of it I was numb. Routine had rounded all the edges off, and if anything I think I might have been in some kind of boreout, and didn’t have a clean way to name it.

What’s happened since hasn’t felt like a slide into burnout, more like an exit out of boredom and a sudden rise in engagement after a long flat stretch. Which is exactly the problem I’m trying to write about : the relief of feeling engaged again is loud enough that it masks the fact that my newly-found engagement doesn’t seem to have an off switch.

My fear is that I might be overcorrecting.

Shipping more than I have in years

At work my managers are noticing, and I’m only getting good feedback from the direct and indirect effect my work has on the team drlivery, engagement and AI tooling adoption.

Outside of work I haven’t been this passionate about shipping things in a long time. Small things, things I actually use, things that make a difference to me and the people around me, things that amuse (only) me. I’m finishing personal projects at a rate I didn’t believe I still had in me and it feels reinvigorating, in a way that maps almost exactly onto the first years of my career, when I was breathing work and loving it.

I keep talking about feeling like I’m in my 20s, because I am, indeed, not in my 20s anymore (let’s say late 30s atp). I have a wife, two young kids, a non-trivial geographical relocation underway, a house to take care of. So should I be as wired into my work as I am (or even can I maintain the long term)?

The honest answer is that I have a framework now that I didn’t have then. My kids and partner are a hard floor preventing me from diving too deep, as the tools would have let me. My sleep schedule has slipped a bit, which is a habit I thought I’d put behind me a decade ago, but I haven’t fully come off the rails and I feel like this structure is doing its job.

This makes me worry for the people who don’t have that structure yet, because if I’d had access to these tools in my 20s, without the floor I built in my 30s, I think I would have broken something. The push for 996 in parts of the silicon valley reads to me as exactly the wrong message to send to people in exactly that situation who will lose themselves inside the work and not notice until it’s too late for them and they are severely burned out.

Passion or compulsion ?

Is what I’m calling reignited passion actually a hyper-fixation based on the constant availability of AI tooling (inside and outside of work) which these past few months has made our phones an even more effective productivity tool ? I used to have a real context switch to get out of work mode, but now there’s no friction, and the same tools that make me productive at the office are sitting on my phone, on my laptop at home, ready to help me ship the next side project at 11pm.

There’s a piece by Armin Ronacher on what he calls agent psychosis that uncomfortably mirrors parts of what I am describing here, and while I’m not ready to put myself in that category, I’m also not ready to claim I’m definitely not on that path.

The water is warm : I’m shipping, my managers are happy, the personal projects I care about are landing.