Florian Schepp

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

www.theregister.com/ai-and-ml/20... very good and very relevant read

Working on a VR game with godot for about 2 weeks now. Playing a lot of the cooking games on the meta quest 3 I have not yet come across one that has multiple dishes, clever challenges, a light and fun story as well as boss fights. More soon! 👀🙌

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

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

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

zed.dev/blog/delta-p... really interesting concept and likely more close to a future of AI and teams working together with less friction

one does not simply reveal a password 👁️

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!

www.bbc.co.uk/news/videos/... Scary but fascinating and shows advancements in robotics.

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...

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

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...

modelmap.cc very nice!

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

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

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

Google launches Gemini 3.6 Flash and 3.5 Flash-Lite, teases Gemini 4 

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

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 👀.

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...

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

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. https://cfl.re/4uJaNji

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...

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

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?

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.

@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🤞

New AI coding benchmark DeepSWE. Very interesting 👀 venturebeat.com/technology/d...

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...

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.

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...

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

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...

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/internal-ai-... very interesting post showing how cloudflare uses their own AI tools now with metrics 👀🙌

github.com/JuliusBrusse... 😄👌

youtu.be/kwSVtQ7dziU?... very interesting interview

maybe gta6 is also too dangerous to release

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...

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 👀