Updates and recent posts about SERP Clapper for Medium..

Posts
Description

Link

@faun shared a link, 1 month, 3 weeks ago

Closer to the Metal: Leaving Playwright for CDP

The Browser-Use crew ditched Playwright and went straight to the Chrome DevTools Protocol. Why? Speed. Way faster element scraping, screenshots, and async automation. They didn't stop there—cooked up a custom CDP Python client with strong type safety, an event-driven core, and real support for crash..

Link

@faun shared a link, 1 month, 3 weeks ago

Le Chat now integrates with 20+ enterprise platforms—powered by MCP—and remembers what matters with Memories.

Le Chat now includes20+ secure, MCP-based connectorsfor tools like GitHub, Snowflake, Stripe, and Jira. That means in-chat search, summaries, and actions—straight from enterprise systems. Developers can plug in their owncustom MCP connectors, and run Le Chat wherever it fits: on-prem, private cloud..

Link

@faun shared a link, 1 month, 3 weeks ago

OpenAI to launch its first AI chip in 2026 with Broadcom, FT reports

OpenAI’s firstin-house AI chipis nearly out of the oven. It’s headed for fabrication atTSMCand built to handle OpenAI’s own workloads—no outside sales, according to theFinancial Times. Why it matters:Big AI shops are going vertical. Custom silicon means tighter control over runtime, reliability, an..

Link

@faun shared a link, 1 month, 3 weeks ago

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

Hugging Face just dropped Kernel Builder—a full-stack toolchain for building, versioning, and shippingcustom CUDA kernels as native PyTorch ops. Kernels arearchitecture-aware,semantically versioned, andpullable straight from the Hub. It tracks changes with lockfiles and bakes inDocker deploysout of..

Link

@faun shared a link, 1 month, 3 weeks ago

GPT-5 Thinking in ChatGPT (aka Research Goblin) is shockingly good at search

GPT-5's“thinking” modeljust leveled up. It's not just answering queries—it’s doing full-on research. Picture deep, multi-step Bing searches mixed with tool use and reasoning chains. It reads PDFs. Analyzes them. Suggests what to do next. Then actually does it. All from your phone. What’s changing:L..

Link

@faun shared a link, 1 month, 3 weeks ago

The Big LLM Architecture Comparison

Architectures since GPT-2 still ride transformers. They crank memory and performance withRoPE, swapGQAforMLA, sprinkle in sparseMoE, and roll sliding-window attention. Teams shiftRMSNorm. They tweak layer norms withQK-Norm, locking in training stability across modern models. Trend to watch:In 2025,..

Link

@faun shared a link, 1 month, 3 weeks ago

Hermes V3: Building Swiggy’s Conversational AI Analyst

Swiggy just gave its GenAI tool, Hermes, a serious glow-up. What started as a simple text-to-SQL bot is now acontext-aware AI analystthat lives inside Slack. The upgrade? Not just tweaks—an overhaul. Think: vector-based prompt retrieval, session-level memory, an Agent orchestration layer, and a SQL..

Link

@faun shared a link, 1 month, 3 weeks ago

Simplifying Large-Scale LLM Processing across Instacart with Maple

Instacart builtMaple, a backend brain for handling millions of LLM prompts—fast, cheap, and shared across teams. It’s not just another service. Maple runs onTemporal,PyArrow, andS3, strip-mines away provider-specific boilerplate, auto-batches prompts, retries failures, and slashes LLM costs by up t..

Link

@faun shared a link, 1 month, 3 weeks ago

Why language models hallucinate

OpenAI sheds light on the persistence ofhallucinationsin language models due to evaluation methods favoring guessing over honesty, requiring a shift towards rewarding uncertainty acknowledgment. High model accuracy does not equate to the eradication of hallucinations, as some questions are inherentl..

Link

@faun shared a link, 1 month, 3 weeks ago

Best Practices for High Availability of LLM Based on AI Gateway

Alibaba Cloud’s AI Gateway just got sharper. It now handlesreal-time overload protectionandLLM fallback routingusing passive health checks, first packet timeouts, and traffic shaping. It proxies both BYO and cloud LLMs—think PAI-EAS, Tongyi Qianwen—and redirects load spikes or failures on the fly. F..

Did you know you can clap for someone’s content up to 50 times on Medium?

Well, you can.

And to protect you from carpal tunnel syndrome, I packaged that behavior into a little extension for Chrome.

It works like this:

https://www.youtube.com/watch?v=oN3soEz-5Z4

Open up your developer tools (right-click & choose inspect)

Then, navigate to the “console”:

And if you have a bunch of caca (that’s Spanish for 💩) in your Console you can click the little 🚫 icon to clear it:

Then:

copy the JavaScript code below
paste it into the Console area
press the Return key

and spread the clap!

(Scroll up to the top of this article before you press enter if you want to see it in action)

let clapButton = document.querySelector('button[data-testid="headerClapButton"]');
if (clapButton) {
const events = ['mousedown', 'mouseup', 'click'];

async function performClap() {
for (let i = 0; i < 50; i++) {
events.forEach(eventType => {
let event = new MouseEvent(eventType, {
'view': window,
'bubbles': true,
'cancelable': true
});
clapButton.dispatchEvent(event);
});
await new Promise(resolve => setTimeout(resolve, 10)); // Introducing a 10ms delay between claps
}
console.log("+50 Claps! Now, go join the SERP community!");
}

performClap();
} else {
console.log("Clap button not found!");
}

Want the extension?

I submitted the extension to the Chrome app store and it’s pending approval as of this writing…

But if you’re too excited to sit around when you could be clappin’ it up — you’re welcome to grab the bootleg here:

👉 https://serp.ly/@serp/serp-clapper-medium