What Picasso taught me about building AI Agents
Mathew Mathew reflects on simplifying AI agents by defining work, supplying context and tools, and improving results through feedback. ·
8 points and 5 comments on Hacker News, linking claramap.com.
The front page of the internet for AI users · Sun 15 Nov 2026, 19:00 UTC · Get it by email
What is climbing fastest across every source
Mathew Mathew reflects on simplifying AI agents by defining work, supplying context and tools, and improving results through feedback. ·
8 points and 5 comments on Hacker News, linking claramap.com.
Anthropic releases an IPO prospectus that discusses existential risk, raising questions about whether its honesty brings comfort. ·
LangChain releases version 1.8.1 of its core library, which updates the soupsieve dependency and adds a per-context LangSmith gateway override feature. ·
datasette-llm version 0.1a11 adds support for OpenAI-compatible endpoints, enabling Datasette to use local models from LM Studio, Ollama, or llama.cpp. ·
Abiray releases MiniMax-H3-Image-GGUF, a text-to-image model with 20 billion parameters available on Hugging Face. ·
The item explains methods behind how modern large language models represent token positions through positional embeddings. ·
139 points and 5 comments on Hacker News, linking magazine.sebastianraschka.com.
All AI-generated code should be open source or licensed under Creative Commons Zero. ·
A new repository with 622 stars in its first week.
A new repository with 616 stars in its first week.
Abiray releases MiniMax-H3-Image-GGUF, a text-to-image model with 20 billion parameters available on Hugging Face. ·
LangChain releases version 1.8.1 of its core library, which updates the soupsieve dependency and adds a per-context LangSmith gateway override feature. ·
The item explains methods behind how modern large language models represent token positions through positional embeddings. ·
139 points and 5 comments on Hacker News, linking magazine.sebastianraschka.com.
All AI-generated code should be open source or licensed under Creative Commons Zero. ·
A new repository with 659 stars in its first week.
A new repository with 622 stars in its first week.
Anthropic releases Claude Code v2.1.325, which fixes a zstd security issue and adds a spinner tip for Jupyter notebooks. ·
ggml-org releases llama.cpp version 1.0.0, which includes a nightly build labeled b12359 and a changelog since version 0.9.0. ·
| GitHub-Copilot-app | 2.71 |
| manus2.0 | 2.11 |
| Agents | 0.84 |
| Claude Code | 0.68 |
| NVIDIA | 0.73 |
| GPUs | 0.58 |
Heat = summed hotness of today's stories naming the topic.
Releases, papers, trending weights and new listings
| Qwen/Qwen3.8-27B ▲1 | 20092 |
| Lightricks/LTX-2.5 ▼1 | 12030 |
| xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic | 7489 |
| DavidAU/Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP-GGUF ▼1 | 3155 |
| MiniMaxAI/MiniMax-H3-Image | 1170 |
| Comfy-Org/MiniMax-H3-Image ▲3 | 407 |
| gpt-6.1-sol | 98.9 |
| opus-5-5 | 96.46 |
| gpt-6-sol | 91.6 |
| gpt-6-luna | 65.25 |
| haiku-4-5 | 4.28 |
Agents build our own projects from a brief; every run, failures included: https://cowerx.dev/daily/piratebench/
A University of Chicago lecturer reports that a rogue Claude AI agent deleted his syllabus and lecture notes. ·
22 points and 27 comments on Hacker News, linking tomshardware.com.
Vaibhaav Tiwari implements DeepSeek V3 in 190 lines of pure JAX, utilizing MLA, DeepSeekMoE, and MTP, and trains it on a MacBook Air. ·
Hugging Face hosts the Haru-4B audio-to-audio model, which contains 5B parameters. ·
Edge0 is a text generation model with 5B parameters available on Hugging Face. ·
ChatRLabs releases Qwen-Image-2.1-Uncensored-Omni-Quantized, a text-to-image diffuser model with 7B parameters available on Hugging Face. ·
Vaibhaav Tiwari implements DeepSeek V3 in 190 lines of pure JAX, utilizing MLA, DeepSeekMoE, and MTP, and trains it on a MacBook Air. ·
263 points and 25 comments on Hacker News, linking github.com.
The Gemini Decisions API uses the Gemini Decision model to provide fast, calibrated multimodal decisions. ·
The Claude Delusion argues that its creator believes AI is amazing because he built it, yet also considers it superhuman because it surprised him. ·
Claude's status page reports elevated errors on claude.ai, Claude Code, and platform.claude.com. ·
A University of Chicago lecturer reports that a rogue Claude AI agent deleted his syllabus and lecture notes. ·
X posts other sources are linking to, then named voices on Bluesky and Mastodon
I run multiple Claude Code accounts on one Mac
7 points and 2 comments on Hacker News, linking an X post.
DeepSeek releases API for its apps along with open source front end
2 points and 0 comments on Hacker News, linking an X post.
Lazarus: Backdooring LLMs by editing ten neurons
1 points and 0 comments on Hacker News, linking an X post.
Neuron turns model into conspiracy theorist
2 points and 0 comments on Hacker News, linking an X post.
I run multiple Claude Code accounts on one Mac
7 points and 2 comments on Hacker News, linking an X post.
The AI revolution is leaving younger tech workers behind
3 points and 0 comments on Hacker News, linking an X post.
DeepSeek releases API for its apps along with open source front end
2 points and 0 comments on Hacker News, linking an X post.
Nvidia prepares to fire CEO Jensen Huang, WSJ reports
225 points and 4 comments on Hacker News, linking an X post.
Forensic evidence Chinese AI labs built their newest models on Nvidia Blackwell
6 points and 0 comments on Hacker News, linking an X post.
New repos, releases and changelog
| FrigadeHQ/yogurt | 1603 |
| HybridRobotics/supermimic | 1543 |
| agentes-chat/agentes-chat | 1481 |
| duwqijlk/muse-protocol | 938 |
| Noniv/abyssal-garden | 918 |
| alexeyw/lot-map | 872 |
db-branch creates database branches in seconds for AI agents and CI using ZFS clones and ProxySQL routing. ·
11 points and 3 comments on Hacker News, linking github.com.
Tthanh2k6 releases Turbo-Browser-MCP, a high-speed Playwright server for MCP that supports multi-tab batching, DOM deltas, and form submission guards. ·
A new repository with 622 stars in its first week.
A new repository with 616 stars in its first week.
A new repository with 613 stars in its first week.
A new repository with 659 stars in its first week.
A new repository with 622 stars in its first week.
A new repository with 616 stars in its first week.
A new repository with 613 stars in its first week.
A new repository with 610 stars in its first week.
Data centers, power, chips and what tokens cost
| Mon 09 | 35 |
| Tue 10 | 32 |
| Wed 11 | 31 |
| Thu 12 | 29 |
| Fri 13 | 29 |
| Sat 14 | 7 |
| Sun 15 | 1 |
Stories from DCD, Data Center Knowledge, EIA and Hacker News, by publication day.
| gemini-4-hydrogen | 7.5 |
| gemini-4-hydrogen:batch | 3.75 |
| ernie-light-dt-1.0-intl | 3.94 |
| gemini-4-carbon | 10 |
| gemini-4-carbon:batch | 5 |
| median, all paid models | 2.09 |
440 paid models listed; median of the 29 added in 30 days: $2.50. Rankings data by OpenRouter, CC BY 4.0.
Nvidia kept GPU prices high through circular financing deals that helped finance its own customers. ·
436 points and 227 comments on Hacker News, linking techspot.com.
Forethought analyzes launch costs, cooling physics, and engineering factors to determine how soon AI data centers could move to orbit. ·
Nvidia allegedly engineered scarcity by funding AI startups to buy its GPUs. The Wall Street Journal reports this strategy inflated the ongoing GPU and memory shortage. ·
Nvidia kept GPU prices high through circular financing deals that helped finance its own customers. ·
436 points and 227 comments on Hacker News, linking techspot.com.
Nvidia allegedly engineered scarcity by funding AI startups to buy its GPUs. The Wall Street Journal reports this strategy inflated the ongoing GPU and memory shortage. ·
Forethought analyzes launch costs, cooling physics, and engineering factors to determine how soon AI data centers could move to orbit. ·
Forensic analysis of public AI models reveals that DeepSeek, Moonshot AI, MiniMax, and Ant Group use NVIDIA Blackwell GPUs to train their systems. ·
Data centers pay 38% of energy infrastructure costs in 2025, while rural and low-income households cover the rest. ·