Thomas Findlay retweeted
ISO 42001:2023 is like the "SOC2 of AI".
It's the first global, independently audited standard for how companies build, evaluate, monitor and govern AI systems.
When you ship on and use Vercel's AI, you now know the infra is audited annually by an accredited third party.
Vercel is now ISO/IEC 42001:2023 certified.
It is the international standard for how companies build, manage, and govern their own AI systems.
vercel.com/blog/vercel-compl…
Thomas Findlay retweeted
a Big Deal buried in Postgres 19 release post
WAIT FOR LSN
clients can now performantly guarantee that the results of a query (run against a replica) reflect all of its previous writes (run against a primary) — this has been the biggest consistency problem with read replicas for years
Ideogram 4.6 is now available on fal
- Applies targeted changes to existing images through written instructions
- Supports edits across product details, clothing colors, illustrated elements and poster typography
- Enables design iteration across both photographic imagery and text-heavy compositions
That looks interesting. Now waiting for actual real-life coding comparisons against Fable and Opus.
Introducing Gemini 4 Neon! Pushing the frontier across domains and punching above its model class in a meaningful way. To me, Neon feels like the right balance of intelligence, speed, and usability. Available now across @GoogleAIStudio, the API, and more!
1
132
Thomas Findlay retweeted
Today we're releasing a new streaming markdown parser called Words. It's built for any markdown, but it's especially useful for streamed llm responses.
@pierre/words is up to 2× faster than md4x, and 20× faster than streamdown. It supports DOM, HTML, and ANSI rendering. It has built in syntax highlighting and renders mermaid charts.
Check it out at diffs.com/words
Thomas Findlay retweeted
AppleがWan2.1ベースの高速動画生成モデル「FastFrames」を公開!!
2ステップ生成で、ワールドモデルの応答が827ms→52ms(約16倍速)。
Appleの研究なのに動作にはNVIDIA GPU(CUDA)が必要なのが面白い👀Appleが中国のオープンモデルを土台に使った」という点も....
huggingfaceの案内では動作にはNVIDIA GPU(CUDA)が必要とのことw
huggingface.co/apple/FastFra…
Thomas Findlay retweeted
Your CI is only as fast as its slowest shard, so split tests by time using vitest
Thomas Findlay retweeted
Introducing Landmines
AI mostly writes useless tests, and no skill file will guarantee it doesn't take the lazy path to getting CI/CD green.
Landmines is a set of Oxlint plugins that let us at @interfere_ go from shipping 100 PRs/week to >1200/week.
github.com/interfere-inc/lan…
Thomas Findlay retweeted
IndexDB isn't cutting it anymore. We've been working on a new client-side database written in Rust using OPFS for our next sync engine in @linear.
It indexes everything. As a drop-in, API-compatible replacement it's faster than IndexDB (which is surprising!), but it absolutely DESTROYS it when you do complex, multi-key queries. And while IndexDB queries slow down linearly as row count increases, our new database stays almost flat. It's like 600x faster with usage we see in Linear, more if you got to large workspaces.
We do want to open-source it, but we can't before we decide on the name. We've got two strong candidates:
- postindex
- sub-linear
Which one do you like more?
Thomas Findlay retweeted
正式开源 OpenMotion🚀!还原度超95%!无需 Fable 5.2 也能复刻爆款视频!
全网首个全栈 Claude Motion & 剪映最佳平替, 浓缩逆向最先进的设计和最好看的模板💥
历时 14 天47w 行代码,支持 100+ 顶尖公司的产品宣传片、300+ 动效版 DESIGN.md,152+设计系统,支持Codex/CC/DSH 等20+AI agent 🔥
Thomas Findlay retweeted
Claude writes better code when it can verify its work. Checks that used to be expensive, like tests, benchmarks, and end-to-end runs, are now cheap.
Here’s how the Claude Code team thinks about verification:
claude.dev/blog/how-the-clau…
Thomas Findlay retweeted
Introducing saved flows in agent-browser
Record a browser task once, then replay it without the browser
→ 13.7 KB of page becomes 328 bytes of data
→ New params on every run
→ Only the fields you ask for
→ Your agent finds them when it opens the site
Thomas Findlay retweeted
New skill: /learn-taste
Collects every design correction you made during a session and turns each one into a strict rule with reasoning, so that the next agent doesn’t make the same mistake.
A great time saver if correct your agent often.
aiforui.dev/skills/learn-tas…
Thomas Findlay retweeted
Introducing Seedream 5.5.
More realistic images. More stable editing across 100 rounds.
1. Keep refining, with pixel-level preservation of unedited regions and reduced detail loss across successive edits.
2. Generate transparent and semi-transparent assets with native RGBA output, ready for compositing and reuse.
3. More natural lighting, materials, and skin textures, with significantly improved small-text rendering.
Seedream 5.5 is coming to Dreamina, CapCut, and BytePlus. We can't wait for you to try it!
Explore what's new: seed.bytedance.com/seedream5…
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
Thomas Findlay retweeted
I made a skill that turns marketing chores into scheduled loops.
A weekly SEO scan with real anatomy: an acts-when condition, a self-check so it doesn't act on noise, a stop rule, and a human checkpoint before anything publishes.
Ideas run once. Loops run forever.
npx skills add coreyhaines31/marketingskills
New in Claude for Legal: a gallery of ready-made artifacts for contract review, regulatory horizon scans, cite checks, and more.
Start from the built-in example, add your own documents and connectors, and share it with anyone across the business.
Thomas Findlay retweeted
Alibaba just open-sourced something insane.
An AI code reviewer that reportedly uses 9x fewer tokens than Claude Code while delivering more precise reviews.
It catches bugs, security flaws, and mistakes before they reach production.
And it's FREE and open source.
It's called Open Code Review.
No paid seats. No vendor lock-in. No AI quietly skipping half the files in your PR.
This was Alibaba's official internal code reviewer for two years. Tens of thousands of their developers used it, and it flagged millions of defects before they released it to the public.
Here's what this thing can do:
→ Reviews your Git diff with comments pinned to the exact line
→ Built-in rules for null pointer bugs, thread-safety, XSS and SQL injection
→ Reads full files and searches your codebase for context, not just the diff
→ Scans whole codebases with no diff needed
→ Plugs into Claude Code, Codex, Cursor, Kimi Code and OpenCode
→ Runs in GitHub Actions, GitLab CI and Gerrit
→ Works with OpenAI and Anthropic compatible models
Here's why it beats general-purpose agents:
Agents that review with prompts alone skip files on big PRs, drift on line numbers, and swing in quality with tiny prompt changes.
Open Code Review hard-codes the parts that can't go wrong. Code picks the files, bundles related ones, and matches the rules. The AI only handles the judgment calls.
Here's the wildest part:
Alibaba benchmarked it on 200 real pull requests from 50 open-source repos across 10 languages. 80+ senior engineers labeled 1,505 real issues.
Same underlying model. Higher precision and F1 than Claude Code. About 1/9 of the tokens. Faster reviews.
The honest trade-off: it finds fewer total issues. On purpose. Less noise, fewer false alarms.
npm install -g @alibaba-group/open-code-review
github.com/alibaba/open-code…



























