iiinova — where your digital self keeps evolving

Florian Schepp @scheppening.com · 29/09/2026

Blackberry and apple never appear in the same sentence. They still end up as nearest neighbors. I built word embeddings from 21 sentences, no pretrained model, and every number is there to check. scheppening.com/posts/click-... #MachineLearning #NLP

011

Reposted by Florian Schepp

Hacker News Bot @newsycombinatorbot.bsky.social · 23/09/2026

The current balance of power in open models (www.interconnects.ai) Discussion | Main Link

011

Florian Schepp @scheppening.com · 23/09/2026

Same query (bsky.app/profile/sche...) for Opus 5.5. TLDR; Create a Barbarian Game character in Blender. Whats with that back though

000

Florian Schepp @scheppening.com · 23/09/2026

GitHub copilot PR review preview in slack: HIGHHH!!! 😄

000

Reposted by Florian Schepp

Jhey ʕ·ᴥ·　ʔ @jhey.dev · 17/09/2026

one does not simply reveal a password 👁️

731934

Florian Schepp @scheppening.com · 17/09/2026

"Overview: Build a single rigged-ready humanoid game character. He is an adult male barbarian/primitive fighter in a low-poly faceted art style, wearing only a burlap loincloth, posed in a standard T-pose. Model the character only, with no environment, floor, backdrop, lighting rig or text."

3D software Blender showing a model that is supposed to be a barbarian low poly npc but looks blocky and more like handsome Squidward from spongebob

100

Reposted by Florian Schepp

zeu @zeu.dev · 15/09/2026

Nuxt’s @danielroe.dev has released a new library and he wants YOU to give it and the AT Protocol a shot! We’re talking about getair.space: cms, auth, file storage, and a public API, all in one! INTERVIEW TODAY, 3PM PST LIVE twitch.tv/zeu_dev stream.place/zeu.dev Ask your Q’s in the replies!

59616

Reposted by Florian Schepp

mr. TIM @timkellogg.me · 21/08/2026

Ox Alpha, a new stealth model on openrouter. People are saying it’s stronger than Sol & Fable. No benchmarks yet. Some are hypothesizing it’s Chinese. Everyone seems convinced that it’s not OpenAI or Anthropic openrouter.ai/stealth/ox-a...

openrouter.ai

Ox Alpha - API Pricing & Providers

Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. This model is free to use. 1,048,576 token context window, maximum output of 131,072 tokens.

10885

Reposted by Florian Schepp

dame @dame.is · 18/08/2026

open models have now surpassed closed models on vercel’s ai gateway the future is open

Open vs. Closed Token Volume

Share of AI Gateway token volume on models that publish their weights for download, versus everything else.

Line chart showing token volume percentage from Jun 20, 2026 to Aug 18, 2026. Blue line represents Open Weights, starting around 40% and rising to 54.3%. Orange line represents Closed Weights, starting around 75% and declining to 45.7%. The lines cross around mid-July 2026, indicating open models surpassed closed models. Y-axis shows percentages from 25% to 100%. Time period options: 2W, 1M, 2M. Chart visualization options available.

0604

Reposted by Florian Schepp

Vladimir @vladimir.berlin · 18/08/2026

An automated AI agent wanted to open a PR in @vitest.dev, but decided against it after reading our updated AI policy. What a marvel to behold github.com/vitest-dev/v...

A comment (diff) with text:

Added:
Written by an AI agent on behalf of @nightcityblade; this comment has not been reviewed by a human.
I discovered the repository policy requiring human involvement and will not submit an automated contribution. This issue remains unclaimed.

Removed:
I would like to work on this and submit a PR shortly.

3436

Florian Schepp @scheppening.com · 18/08/2026

Guess I was sleeping on the movie "The creator".

000

Florian Schepp @scheppening.com · 16/08/2026

blog.alaindichiappari.dev/p/what-to-do... interesting read. I hope when value engineering for ram as well as engineering more efficient language models increases this becomes less of an issue and everyone has adequate default models being able to run on their personal computers

blog.alaindichiappari.dev

What to do when tokens run out

If in the '80s we fought to squeeze a program into a few kilobytes, we now have to squeeze the most useful LLM work into the tokens we can afford. You ready?

000

Reposted by Florian Schepp

VoidZero @voidzero.dev · 22/07/2026

Type-aware Linting via Oxlint is now stable 🎉 oxc.rs/blog/2026-07...

oxc.rs

Type-Aware Linting Stable

A collection of high-performance JavaScript tools written in Rust

220728

Florian Schepp @scheppening.com · 18/07/2026

"We bet on open the first time. Open won. Together, we can do it again." - stateofopensource.ai

stateofopensource.ai

The State of Open Source AI — V1.0 · July 2026

110

Florian Schepp @scheppening.com · 17/07/2026

Did anyone actually get ternary bonsai 27b to run with eg. Pi or opencode? Trying to set up with pi and it just keeps "working..." When I just wrote "test". Mac M4 32GB and it works itself up to using 12GB instead when setup via uv and MLX. So far no luck getting something out of it 👀.

000

Reposted by Florian Schepp

Sung Kim @sungkim.bsky.social · 14/07/2026

1-bit LLM Bonsai 27B, shrinked from 54GB to just 3.8GB (-93%), runs locally in your browser Models: huggingface.co/collections/... Demo: huggingface.co/spaces/webml...

huggingface.co

Bonsai 27B - a prism-ml Collection

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

68211

Florian Schepp @scheppening.com · 02/07/2026

Even Sonnet 5 now being more expensive than Opus 4.8. uff.

010

Reposted by Florian Schepp

Cloudflare @cloudflare.social · 19/06/2026

The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds. cfl.re/4uJaNji

blog.cloudflare.com

Temporary Cloudflare Accounts for AI agents

Agents can now deploy websites, APIs, and agents right away, without first needing to sign up for an account.

0112

Reposted by Florian Schepp

Ground News @groundnews.bsky.social · 16/06/2026

Bots now make up 57.5% of web traffic to HTML pages, topping humans at 42.5%, according to web hosting platform Cloudflare. ground.news/article/bots...

36633

Reposted by Florian Schepp

Justin Schroeder @jpschroeder.com · 23/03/2026

We’re open sourcing ArrowJS 1.0: the first UI framework for coding agents. Imagine React/Vue, but with no compiler, build process, or JSX transformer. It’s just TS/JS so LLMs are already *great* at it. AND run generated code securely w/ sandbox pkg. ➡️ arrow-js.com

7557

Florian Schepp @scheppening.com · 11/06/2026

People saying with anthropics mythos AI models are not affordable anymore. I've not even used Opus 4.7 or 4.8 yet seeing Opus 4.6 eat my tokens a couple times. What's new?

000

Reposted by Florian Schepp

VoidZero @voidzero.dev · 04/06/2026

VoidZero is joining Cloudflare. Our mission stays the same: to make JavaScript developers more productive than ever before. Vite, Vitest, Rolldown, Oxc, and Vite+ remain MIT-licensed. Evan and the VoidZero team will continue leading them.

1027756

Florian Schepp @scheppening.com · 02/06/2026

@thdxr.com the pragmatic engineer interview was very interesting and was wondering when there'll be new info about opencode enterprise? Would love to see how it compares to a cloudflare AI gateway + worker proxy setup. Saw the trial option but would love to have some more info before doing that🤞

000

Florian Schepp @scheppening.com · 27/05/2026

I am using Kimi k2.6 on deepinfra via cloudflare AI gateway (BYOK) and proxy worker for rate limitation (e.g. budget protection and logging token outputs). Its the first time I use a cheaper (not Google, openAI, Anthropic) model and I wonder does DeepSeek v4 also sometimes just stop during thinking?

210

Florian Schepp @scheppening.com · 26/05/2026

Uber blew its budget, MSFT is cutting Claude, & GitHub/Anthropic are moving to metered billing. DeepSeek or Kimi only buy time. The real issue is context bloat & MCP tool baggage. For more info: scheppening.com/posts/the-po... #AgenticAI #TokenEconomics #ModelContextProtocol

scheppening.com

The Post-MCP Era: Token Economics, Context Bloat, and the No-MCP Shift | Scheppening.com

Explore how to build an MCP server, the hidden costs of context bloat, and why token economics are driving the "No-MCP" shift in lean agentic engineering.

130

Florian Schepp @scheppening.com · 20/05/2026

GeminiCLI becomes AntigravityCLI Google Antigravity 2.0 agent view first overhaul with a bunch of new features Google AI studio app now allowing building native android apps Gemini 3.5 flash (will later be followed by 3.5 pro) And some more: developers.googleblog.com/all-the-news...

developers.googleblog.com

All the news from the Google I/O 2026 Developer keynote- Google Developers Blog

Discover how Google is redefining development at I/O 2026. Explore the new Gemini 3.5 series, the Antigravity 2.0 agent platform, and cutting-edge AI agent tools for building, migrating, and optimizin...

000

Reposted by Florian Schepp

Google for Developers @developers.google.com · 05/05/2026

Gemma 4: Now up to 3x Faster. ⚡ Same quality, way more speed. Our new MTP drafters allow Gemma 4 to predict multiple tokens at once, effectively tripling your output speed without compromising intelligence.

410713

Reposted by Florian Schepp

Orion Reed @orionreed.com · 02/05/2026

The nascent HTML-in-Canvas API is exciting to me not because of flashy effects, but because it extends the semantics that the DOM can (tractably) represent — as a tiny example, it's possible to show an element in multiple places, cheaply, under arbitrary transforms. folkjs.org/demos/html-i...

2051785

Reposted by Florian Schepp

pnpm @pnpm.io · 27/04/2026

Added pnpm Pacquet to the benchmarks github.com/pnpm/pacquet

1685

Reposted by Florian Schepp

daniel sieradski @self.agency · 27/04/2026

and now github copilot. the era of subsidized a.i. is over.

To keep up with the way you use Copilot, we're transitioning to usage-based billing, and we want to give you enough time to prepare. If you're also an admin on a Copilot Business or Enterprise plan, you'll receive a separate email covering what's changing for your organization.

Last week, we made temporary updates to Copilot individual plans to improve reliability and performance ahead of the broader move to usage-based billing. We will loosen usage limits once usage-based billing is in effect.

What's changing on June 1

Premium request units, or PRUs, will be replaced by GitHub AI Credits which are a monthly allotment of credits consumed based on token consumption (input, output, and cached tokens) according to the listed API rates per model. This change aligns Copilot pricing with actual usage and is an important step toward a sustainable, reliable Copilot business and experience for all users.
Copilot code review’s agentic architecture runs on GitHub Actions. Copilot code review will now consume GitHub Actions minutes, in addition to GitHub AI Credits. These minutes are billed at the same per-minute rates as other GitHub Actions workflows.
Fallback experiences will no longer be available. Under the new model, usage will instead be governed by available credits.

Your plan pricing is unchanged: Copilot Pro remains $10/month and Pro+ remains $39/month, and each includes $10 and $39 in monthly AI Credits, respectively. Code completions and next edit suggestions stay included in all plans and do not use AI Credits. For other features, you'll need to wait for your monthly included usage to reset, purchase additional usage, or upgrade your plan.

1021863

Reposted by Florian Schepp

TypeScript @typescriptlang.org · 21/04/2026

TypeScript 7.0 Beta is here! Built on a new native and parallelized foundation, it's already being used on multi-million line codebases. Read up more here and try it on your projects today! devblogs.microsoft.com/typescript/a...

devblogs.microsoft.com

Announcing TypeScript 7.0 Beta - TypeScript

Today we are absolutely thrilled to announce the release of TypeScript 7.0 Beta! If you haven’t been following TypeScript 7.0’s development, this release is significant in that it is built on a comple...

232773

Florian Schepp @scheppening.com · 21/04/2026

Sorry one more in regards to Cloudflare automating their PR reviews with AI also with interesting metrics blog.cloudflare.com/ai-code-revi... . Guess it's going to be one of those weeks where I can't keep up with reading the news 😂🙌

blog.cloudflare.com

Orchestrating AI Code Review at scale

Learn about how we built a CI-native AI code reviewer using OpenCode that helps our engineers ship better, safer code.

000

Florian Schepp @scheppening.com · 20/04/2026

I am sure everyone has done things with a browser connected to an agent. Found this article particularly helpful showing the differences between playwright and chrome devtools as valid options.: stevekinney.com/writing/driv...

stevekinney.com

Playwright vs. Chrome DevTools MCP: Driving vs. Debugging | Steve Kinney

Playwright and Chrome DevTools both ship official tools for letting AI agents drive a browser, but they're optimized for different jobs. Here's how Playwright CLI, Playwright MCP, and Chrome DevTools ...

100

Reposted by Florian Schepp

dax @thdxr.com · 09/04/2026

maybe gta6 is also too dangerous to release

2557

Reposted by Florian Schepp

Sung Kim @sungkim.bsky.social · 08/04/2026

Meta Superintelligence Labs's Muse Spark (closed-weight?) Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration. ai.meta.com/blog/introdu...

1171

Florian Schepp @scheppening.com · 08/04/2026

Anthropic.com/glasswing sounds great but the promotion of Claude Mythos as part of this, although promising benchmark results, kind of takes away from what sounds initially like a generally good partnership promise. Curious what Google and others will counter with a new model of theirs 👀

anthropic.com

Project Glasswing: Securing critical software for the AI era

A new initiative to secure the world’s most critical software and give defenders a durable advantage in the coming AI-driven era of cybersecurity.

000

Reposted by Florian Schepp

Antropia @antropia.bsky.social · 06/04/2026

What if the exhaustion everybody feels isn't a moral failure but the completely rational response to being made responsible for an ecosystem of objects that never stop asking? Beautifully written @terrygodier.bsky.social www.terrygodier.com/the-last-qui...

terrygodier.com

The Last Quiet Thing

Your possessions came alive. Now they won't stop talking.

0125

Reposted by Florian Schepp

Google Open Source @opensource.google · 02/04/2026

The #Gemmaverse just got more open! With Gemma 4 now under the Apache 2.0 license, we're providing the autonomy and clarity developers need to build breakthrough innovations. What does this unlock for you? #OpenSource #AI goo.gle/gemma-4-apac...

goo.gle

Google releases Gemma 4, expanding the Gemmaverse with Apache 2.0-licensed AI models. Learn how this empowers developers and researchers.

1106

Florian Schepp @scheppening.com · 24/03/2026

In awe of JJ as git compatible version control system. Just takes some time to get used to the new commands 👀

000

Reposted by Florian Schepp

Node.js @nodejs.org · 10/03/2026

Node.js is moving to one major release per year starting with Node 27! 🚀 ✅ Simpler: Every release becomes LTS. ✅ Predictable: Version numbers now align with the year. ✅ New: A 6-month Alpha channel for early testing. bit.ly/4rnosLg

nodejs.org

Node.js — Evolving the Node.js Release Schedule

Node.js® is a free, open-source, cross-platform JavaScript runtime environment that lets developers create servers, web apps, command line tools and scripts.

423360