We’re live. Meet TenPayGo 👋
Coming to China for travel?
TenPayGo is a payment app built by Weixin Pay for overseas visitors to China. Pay wherever Weixin Pay is accepted, using Apple Pay, international cards and supported e-wallets.
Sign up with your email and you’re ready to go.
And there’s more — from translation to metro and bus travel, TenPayGo is built to make everyday life in China easier.
Easy Pay with TenPayGo.
Explore China with TenPayGo.🇨🇳
duh retweeted
I am a sucker for good books, and so especially O'Reilly books.
Here's one that is WIP, but in return, it is free, thanks to @AntithesisHQ
It's for CTOs / eng leaders who want to get AI to deliver *business value* which is... tricky.
Get it here:
pages.antithesis.com/oreilly…
🤝 Paid partnership
duh retweeted
useful tip for Opus 5.5:
run “/claude-api prompt-audit” in Claude Code. this checks you skills, agent.md, Claude.md, prompts and removes anti-patterns that hobble frontier models.
i updated the skill w/ the latest Opus 5.5 guidance.
duh retweeted
【Playwright導入でE2Eテストを373件から829件に増やし、実行時間を1/5に高速化】
#Playwright #findy_tools
🔗findy-tools.io/products/play…
duh retweeted
Claude Opus 5.5 (max) costs $5.98 per Intelligence Index task, which is similar to Opus 5 (max) at $5.86, but this bundles a significant token usage increase with Anthropic’s price reductions
Compared to Opus 5, Opus 5.5’s increased token usage would drive an ~80% increase in cost per task to $10.51. However, the 20% cut to base prices takes that to $8.41, and then cutting cache reads further to $0.20 takes it to $5.98 (an additional 29% cut)
duh retweeted
tanteki: 業務のための文書をもっと端的にするSkill
iwasa-kosui.github.io/tantek…
長ったらしい文書に悩んでいませんか？
論点が曖昧なADR、なぜか作業の進捗が書かれたDesign Doc、現在の実装を詳説した手順書...
文書の種類ごとに、書くべき情報を絞って執筆する「tanteki」をリリースしました。
CI on Cloudflare!!!!!
ArtifactsとかCloudflare Computer来てたから来るだろうなと思ってたけど、気付いてなかった
内部実装見てると、Cloudflare ComputerじゃなくてSandbox + キャッシュで、人間向けのCIではなくて、Agent向けのイベント駆動型のCIだな(そりゃそう)
github.com/cloudflare/ci
duh retweeted
Introducing Xiaomi MiMo-V2.6 — Pro & Flash.
Frontier intelligence, all the modalities, built in public.
🔹 Two omnimodal models, advancing through scaled reinforcement learning
🔹 Pro performs on par with Claude Opus 5 and GPT-5.6 Sol across most agent benchmarks
🔹 Pro scores 46 on the Artificial Analysis Intelligence Index — the highest among open-source models
🔹 Stronger coding, computer use, 3D reasoning and creative capabilities
🔹 Open model weights, technical report, RL environments and training code
Blog：mimo.xiaomi.com/mimo-v2-6
duh retweeted
Your job may be surviving on inertia. Your resentment won’t extend the runway. What do you actually want to do with the intelligence now at your disposal?
duh retweeted
github.com/githubnext/localj…
Not everyone on the team has access to Jev yet. Spent a morning cobbling together a poor man's Jev on top of omlx for local use. Benchmarked and eval'ed a variety of models including diffusiongemma and a variety of autoregressive models (Qwen MoE, Gemma 4 MoE, and Gemma 4 e4b/e2b.) Benchmark report is in the repo.
This is 100% promptcoding but hey the evals look okay, speeds are pretty good on local machine (m5 max 64gb), and the LocalJev server exposes an API that can be used with the normal Jev API wrapper libraries.
duh retweeted
UPDATE: Kev-0.6B, 4B, and 8B are now available. Kev is a family of small open source Jev-like decision models you can train and run yourself.
This new family is based on Qwen3 using the same LoRA + small pointer head technique as before, but scaled up.
Out of domain, on data Kev never trained on: Kev-8B 79.6%, Jev 85.7%.
• Drop-in TypeSafe System One API; their SDK works with one `base_url` change
• Kev-4B serves on a 32 GB Mac in bf16: ~300 ms for five questions, ~40 ms on an H100
• Repeated documents hit a KV cache: 2-2.5x faster
• Apache 2.0 License. Kev-4B trains in 40 minutes on one H100. Kev-8B in 83 minutes.
Code, weights, evals: github.com/jaredpalmer/kev
Kev-0.5B: A tiny open source Jev-like decision model with a TypeSafe-compatible API based on Qwen2.5-0.5B that you can train and run on a MacBook Pro.
Model card and weights are available on GitHub
github.com/jaredpalmer/kev
duh retweeted
"DiffusionGemma as Jev" showcases the power of non-autoregressive architectures.
While Jev demonstrates the value of rapid decision models, running DiffusionGemma in this paradigm leverages canvas diffusion to evaluate structured choices in a single parallel pass:
⚡ ️Massive Parallelism: Denoises across an open canvas in a single step instead of sequential autoregressive token generation (~0.2s on a DGX spark).
🧠 Full Bidirectional Attention: Allows every option to attend to the full context concurrently, yielding well-calibrated decision distributions.
👁️ Multimodal Grounding: Inherits Gemma 4's spatial vision capabilities for complex visual and text decisions.
Read more about this approach here:
github.com/vllm-project/vllm…
nitter.cf/mmastrac/status/210037…
nitter.cf/mmastrac/status/210062…
duh retweeted
お❗️GitHub Actions を実行（トリガー）できるアクターを限定できる機能が GA になった
Workflow execution protections in GitHub Actions generally available - GitHub Changelog
github.blog/changelog/2026-0…
duh retweeted
I just saw Cloudflare launched Quick Tunnels
"One command turns the server on your laptop into a public, encrypted URL on Cloudflare's edge. No account. No DNS. No open ports."
try.cloudflare.com
duh retweeted
got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second
6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5
paste a diff → ONE call to @typesafeai → 14 typed checks come back as probabilities:
hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, blast radius, reviewer effort…
code turns that into a verdict: BLOCK / security review / nits / merge. anything a critical check isn't sure about (0.35–0.65) gets escalated to a human or a big model instead of guessed
duh retweeted
still waiting my invite @typesafeai
🤖 Made with AI
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
duh retweeted
whoa this actually worked! Jev lets me control my browser in real time with my voice now
> i talk
> transcript sent to Jev
> jev returns probabilities in ~300ms
> browser clicks
costs: $0.0002 per decision
i'm stunned how fast this is. when i asked it to "go back", it even finished the request before i finished my sentence 😂
Today, we’re announcing Ternary Bonsai 2 27B.
Based on Qwen3.8 27B, Bonsai 2 27B is 9x smaller than its full-precision counterpart while retaining 98.2% of its aggregate benchmark performance.
Two months after the first Bonsai 27B release, the biggest change is quality. The footprint remains 5.9 GB, but the gap to full precision has narrowed materially, with particularly strong gains in agentic coding, multimodal reasoning, and long-horizon tool use.
Ternary Bonsai 2 27B is available today under Apache 2.0.
