HN user
Setup a quick CDP connection. Have Claude Code attach and inject JS into Page.addScriptToEvaluateOnNewDocument. Loads before the page.
Typical early hooks: • fetch wrapper • XMLHttpRequest.prototype.open/send wrapper • WebSocket constructor wrapper • history.pushState/replaceState wrapper • EventTarget.addEventListener wrapper (optional, heavy) • MutationObserver for DOM diffs • Error + unhandledrejection capture
The good ole VC OS Rug Pull. Classic.
It’d be nice if Mozilla (or a similar foundation) could create a baseline OS platform for a business communications suite.
I'm neither and have 2. 24/7 async inference against github issues. Free. (once you buy the macs that is)
absolutely f ads
none of it will matter soon. anything you want to see or watch will be dynamically generated just for you. enders game is here.
they need domestic chip capabilities
lower is better
https://github.com/frarees/typometer
Typometer
Typometer is a tool to measure and analyze the visual latency of text editors.
Editor latency is the delay between an input event and a corresponding screen update — in particular, the delay between keystroke and character appearance. While there are many kinds of delays (caret movement, line editing, etc.), typing latency is a major predictor of editor usability.
Check the article typing with pleasure to learn more about editor latency and its effects on typing performance.
hook up zen mcp to openrouter and use cerabras inference with kimi k2 and qwen3 480b at 2k tok/sec
is the author secretly the ceo of htmx?
entity resolution is the killer feature. context engineering is the problem with this benchmark attempt. The agent plan seemed to one shot, and the fact that the LLMs could write their own tools without validation or specific multi shot examples is worrisome. To me way to much left to the whims of the llms - with out proper context.
XUL! why not just use htmx and the platform?
This is awesome! Why bun over deno? Curious your decision making process there. Making a similar but opposite decision there.
Not a dev, but I know what these are. Maybe the post was meant for people that know. Bun / deno new nodejs. Hono new koa new express. Vite new webpack. React still React but most popular.
Is there anything like this or pocketbase for MongoDB?
Social science isn’t really social science. It’s all mentalism
So cool! Vision Pro version?
Looking forward to Linux for my gaming box
Challenger sale
We’re gonna have so much local inference available.
Knowledge / property graphs provide truths that can guide the retrieval. LLMs lack a truth function, ie causality. The KPG provides this as sorta a lace across the llm vector space. A KPG can either be used as a filter or a router of sorts. I expect we’ll see kpgs colocated with vector data of the llm and a tuned router layer uses it to guide retrieval and course correct the output. Kind of like MoE.
The price is amazing though $43+$20 shipping. A Pi-KVM v4 Mini is $274 with free shipping in the US.
No open source firmware is definitely a no-go
This is a shit article.
Helium leak is in the trunk. They jettison that on return, so only way to debug is to stay at the station for a few a days. Well within parameters.
They are cleared to depart if an emergency.
This should be the top comment
Do you have any examples of the kind of questions it can answer using a graph backend vs tradition rag and chunking?
Did you test different embedding / chunking strategies of the RAG vector db?
Is the KG vectorized?
it's dead Jim
MLX on silicon rocks, now imagine tuned neural engines to transformer or mamba architectures. Yes it’s just matrix multiplication, but they can optimize the chips for their level of precision, memory bandwidth and unified memory. Not to mention the future of ai is an electric power battle, who outperforms everyone on performance per watt?
The ads are so bad. These sites are in their own doom spiral. We need more revenue due to falling readership. I know more ads!
I can’t wait to filter the entire internet with on device AI.
The universal site & ad blocker.
Inb4, iOS safari blockers suck or I haven’t found a good one. Biggest benefit of side loading is compile your own Firefox and run unlock origin.
Hmm, AS400’s are back!
I think we’re going to see a greatly increased use of FPGAs in AI applications. They can be very good at matrix multiplication. Think about an AI layer that tunes the FPGA based on incoming model requirements? Need an LPU like groq? Done. I would bet Apple Silicon gets some sort of FPGA in the neural engine.