X

Articles from X

Cards List

@oragnes: Holy shit, my AI finally made me money — Codex + Opus is unbeatable

X AI KOLs Timeline · 19h ago Cached

A user shares their experience of successfully making money with AI using the Codex and Claude Opus combo, calling it an unbeatable combination.

0 favorites 0 likes

@QingQ77: A terminal AI coding agent designed specifically for DeepSeek API prefix caching mechanism, maintaining ultra-low token costs in long sessions through a cache-first architecture. https://github.com/esengine/DeepSeek-Reasonix… Reaso…

X AI KOLs Timeline · 19h ago Cached

Reasonix is a terminal AI coding agent designed specifically for DeepSeek API prefix caching mechanism, achieving ultra-low token costs in long sessions through a cache-first architecture. In testing, 435 million input tokens cost only about $12, with a cache hit rate of 99.82%.

0 favorites 0 likes

@ickma2311: Efficient AI Lecture 12: Transformer and LLM This lecture is not only about how LLMs work. It also explains the buildin…

X AI KOLs Timeline · 19h ago Cached

Lecture notes from an Efficient AI course covering Transformer and LLM fundamentals, including multi-head attention, positional encoding, KV cache, and the connection between model architecture and inference efficiency. The content explains how design choices in transformers affect memory, latency, and hardware efficiency.

0 favorites 0 likes

@elliotchen100: Thariq from Anthropic’s viral HTML post hit 1.5M reads. On the surface, it’s about formatting aesthetics, but he’s actually outlining a brand-new workflow. Picking out the most technical points. First, HTML isn’t a document; it’s a throwaway editor. Take his example…

X AI KOLs Timeline · 19h ago

Analyzes a new AI development workflow shared by Anthropic employee Thariq, highlighting how replacing Markdown with HTML and SVG can dramatically improve multi-agent collaboration and interaction efficiency, offering a model better suited to human-AI synergy in the AI era.

0 favorites 0 likes

@libapi_: Today, Hermes Agent secured the number one spot globally. This isn't just a ranking—it reflects the combined push from the open-source community, developers, contributors, and every real user. I'm also thrilled to see more AI Agent projects on @OpenRouter gaining visibility. CLI, Personal Agents, automated workflows, …

X AI KOLs Timeline · 19h ago

Hermes Agent tops the global rankings, highlighting the collaborative drive of the open-source community and developers, while signaling that the AI Agent ecosystem is rapidly scaling across platforms like OpenRouter.

0 favorites 0 likes

@ctatedev: Introducing zero-native Build native desktop + mobile apps with web UI and Zig → Tiny binaries, low memory usage → Sele…

X AI KOLs Timeline · 20h ago Cached

zero-native is a new tool for building native desktop and mobile apps using web UI and Zig programming language, featuring tiny binaries, low memory usage, and support for multiple web engines (WKWebView, WebKitGTK, WebView2, Chromium/CEF) and frameworks (Next.js, Vue, Svelte, Vite, React).

0 favorites 0 likes

@Teknium: We just hit number one globally across all AI apps on OpenRouter. Super grateful to the nearly 1000 contributors who've…

X AI KOLs Following · 20h ago Cached

The Hermes Agent model has reached the top global ranking across all AI applications on OpenRouter, powered by contributions from nearly 1,000 developers. The creator thanks the community and invites suggestions for future improvements.

0 favorites 0 likes

@NousResearch: Hermes Agent is now #1 on the Global @OpenRouter token rankings. While our journey together has just begun, we'd like t…

X AI KOLs Following · 20h ago Cached

Hermes Agent from NousResearch has reached #1 position on OpenRouter's global token rankings, marking a significant achievement for the AI agent.

0 favorites 0 likes

@rohit4verse: Karpathy second brain is the highest leverage tool nobody uses correctly. it should brief you every morning with the co…

X AI KOLs Timeline · 20h ago

A Twitter post discussing Andrej Karpathy's second brain system using Obsidian and Claude Code for automated knowledge capture and daily briefings as a productivity workflow.

0 favorites 0 likes

@levie: A common trend emerging in larger enterprises is token budgeting as a major topic. As agents can do more and more long …

X AI KOLs Following · 20h ago

The article discusses the emerging trend of token budgeting in enterprises, highlighting the need for new management tools as AI agents consume significant compute resources. It suggests this will create a startup opportunity for software solutions that provide visibility and control over agentic spend.

0 favorites 0 likes

@Tesla: Tesla Vision allows us to deploy airbags up to 70 milliseconds earlier if your Tesla detects an unavoidable collision T…

X AI KOLs Following · 20h ago Cached

Tesla announces its Vision system can detect unavoidable collisions and deploy airbags up to 70 milliseconds earlier, potentially making the difference between serious injury and walking away from a crash.

0 favorites 0 likes

@RhysSullivan: I'm now building Executor full time as a startup! The state of tool calling is a mess: - Everyone is using different ag…

X AI KOLs Timeline · 20h ago Cached

Rhys Sullivan is building Executor, an open-source integration layer for AI agents that provides a unified tool catalog with access controls, approval flows for destructive actions, and support for MCP, OpenAPI, GraphQL, and more. It aims to standardize tool calling across different agents like Cursor and Claude Code.

0 favorites 0 likes

@yoheinakajima: the new http://di.gg looks great!

X AI KOLs Following · 20h ago Cached

This is an aggregation of trending AI news from Digg, covering topics such as Neuralink brain implants, NVIDIA's performance fixes for Claude Code, Anthropic's policy stances, and the release of Flowception video modeling code.

0 favorites 0 likes

@JulianGoldieSEO: Google just made local AI 3x faster for FREE. Gemma 4 now runs fast enough on normal laptops that local AI finally feel…

X AI KOLs Timeline · 20h ago

Google released Gemma 4, an open-source AI model optimized for local execution on standard laptops, offering 3x faster performance and a 256k context window for free under an Apache 2.0 license.

0 favorites 0 likes

@slash1sol: ChatGPT 5.5 is cooked. Claude Opus 4.7 is cooked. Every $420/mo SaaS AI just got an open-source assassin. Mind blown: a…

X AI KOLs Timeline · 20h ago Cached

OpenHuman is an open-source desktop AI agent that runs locally on your machine, offering privacy-focused integrations with apps like Gmail and Slack, and challenging subscription-based SaaS AI models.

0 favorites 0 likes

@jawwwn_: .@elonmusk on aliens, and how to make civilization last 100+ years: “Why have we not seen any aliens? It could be becau…

X AI KOLs Following · 21h ago Cached

Elon Musk discusses the Fermi paradox and the rarity of intelligence as a possible explanation for why we haven't encountered aliens, in a conversation shared via Y Combinator and Garry Tan.

0 favorites 0 likes

@Snixtp: More efficiency tests on a single 3090 TL;DR: - I tested 8 local LLMs on a single RTX 3090, power limit from 100W to 45…

X AI KOLs Following · 21h ago

The article presents benchmark results for 8 local LLMs on an RTX 3090, showing that power efficiency peaks around 225W, with diminishing returns at maximum power.

0 favorites 0 likes

@reach_vb: in the last ~15 days we shipped: - gpt image 2 - privacy filter - gpt 5.5 - gpt 5.5 pro - gpt 5.5 instant - gpt realtim…

X AI KOLs Following · 21h ago Cached

OpenAI shipped multiple GPT models and features in approximately 15 days, including GPT Image 2, various GPT 5.5 variants (pro, instant, cyber), GPT Realtime 2, and related tools.

0 favorites 0 likes

@ClaudeDevs: We're co-hosting a couple of hackathons in San Francisco next week. Come build with Claude

X AI KOLs Following · 21h ago Cached

Anthropic is co-hosting hackathons in San Francisco next week, inviting developers to build with Claude.

0 favorites 0 likes

@WSInsights: A 25-year-old podcast host over the past two years has interviewed the key figures from top AI labs like OpenAI, Anthropic, and DeepMind. Karpathy, Hassabis, Dario Amodei, Ilya Sutskever — all the big names in the field...

X AI KOLs Timeline · 21h ago

25-year-old podcast host Dwarkesh Patel has interviewed key figures from top AI labs including OpenAI, Anthropic, and DeepMind, such as Karpathy, Hassabis, Dario Amodei, and Ilya Sutskever. He publicly shared his AI-assisted "one-week preparation" workflow: having AI列出必读资料, tracking gaps in understanding, using AI to map out the full landscape, and implementing the code himself. Time magazine included him in the "AI 100" list for 2024.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback