Thomas Findlay (@thomasfindlay94) header
Thomas Findlay (@thomasfindlay94) profile picture

Follower of Jesus. CTO & Technical Lead. The author of React & Vue - The Road To Enterprise books. https://teapawt.net/t.co/OabK1Ly62V

London, England
Joined November 2016
Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)Photo by Thomas Findlay (@thomasfindlay94)
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 🔥
112
164
60
1,225
89,028
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…
312
754
204
12,749
1,182,956
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
27
30
10
539
56,349
Thomas Findlay retweeted
Introducing the UI SDK.
217
433
242
6,562
878,846
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…
92
111
14
3,154
80,614
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…
76
150
122
1,441
410,611
Thomas Findlay retweeted
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.
3,177
9,245
6,961
96,253
20,150,021
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
19
3
1
24
2,604
Thomas Findlay retweeted
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.
897
2,204
1,497
31,771
8,098,096
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…
90
154
24
1,316
76,306
Thomas Findlay retweeted
The Agent SDK is now available. Define agents as code, with prompts in Markdown and tools in TypeScript. Deploy them on our hosted infrastructure, or run them on your own. Built-in evals let you measure every change and make your agents better over time.
422
280
278
3,934
416,687
Thomas Findlay retweeted
If you've ever wondered why smart TVs are so cheap, this is why. @log4j rooted his Samsung and found an always-on hot mic, automatic content recognition, geolocation, network mapping, ad targeting and user profiling, shared with Samsung's "400 partners". A lot of it can be blocked in <15 min, wrote a basic guide below. What your TV is doing The main culprit is ACR (automatic content recognition). Your TV screenshots what's on screen, fingerprints it, and sends it home to build your ad profile. Samsung does it every 500ms, LG every 10ms [1]. What is insane: it happens on connected devices too. Plug in your laptop, your console, your work machine, and your TV can fingerprint that via HDMI [1]. He also found that if your Samsung doesn't have a mic, it'll look for one from a connected soundbar or bluetooth device. teapawt.net/log4j/status/211376224… It's on by default, and you likely agreed to it on the setup screen you clicked through in 10 seconds. Step 1: Turn off ACR Samsung: Terms & Privacy → Viewing Information Services LG: Live Plus Vizio: Viewing Data Roku: "Use info from TV inputs" Sony/Google TV: Samba Interactive TV Menus vary by model, but those are the names to look for. While you're in there, opt out of interest-based ads, reset your advertising ID, decline every optional privacy agreement, turn off voice recognition, and delete apps you never open. Step 2: Give smart devices their own network Put the TV, cameras, speakers and vacuum on your router's guest/IoT network. The logic is simple: these devices rarely get patched. If one gets compromised (getting drastically more frequent with AI), it shouldn't be able to see your other devices or home network. Step 3: Block trackers for the whole house with DNS-level filtering NextDNS (cloud-based) is easy and has a solid free plan. Pi-hole is a little bit more work if you prefer self hosting. For simplicity we'll focus on the former. 1. Sign up at nextdns.io (free tier is plenty) 2. Privacy tab: add a blocklist (OISD is a good bet) and turn on Native Tracking Protection for Samsung, LG, Roku, Amazon (see attached image) 3. Setup tab: copy your endpoint 4. Paste it into your router's DNS settings as DNS-over-HTTPS/TLS (or use the IPs + "Link IP" if your router only does plain DNS) 5. Bonus: block outbound port 53 except to your router. Some devices hardcode their own DNS to get around you Then open the NextDNS logs and watch how often your TV phones home. It's eye-opening. If an app or update breaks, find the domain in the logs and allowlist it. Why they do this TV prices are down 97% since 2000 [2]. Most of that is better manufacturing and brutal competition. But once margins on the hardware hit zero, the cost moved to you. In Q3 2024, Vizio lost $6.7M selling TVs and made $115.8M in gross profit from ads and viewing data [3]. They've said on earnings calls that they keep TV prices low to grow the audience they sell to advertisers. Walmart bought them in 2024. This isn't a conspiracy theory either. Vizio paid $2.2M to the FTC in 2017 for tracking 11 million TVs without consent. Last December, Texas sued Samsung, LG, Sony, Hisense and TCL over ACR. Samsung and LG have since agreed to stop collecting that data without explicit consent [4]. TL;DR 1. ACR off 2. Ads + voice off 3. Smart devices on their own network 4. NextDNS filtering on the router Sources: [1] ACR study: arxiv.org/abs/2409.06203 [2] Cost of US consumer goods: aei.org/economics/chart-of-t… [3] Vizio Q3 2024: sec.gov/Archives/edgar/data/… [4] Texas v. Samsung: texasattorneygeneral.gov/new…
i own a relatively new (2025) samsung tv. i kept getting weirdly targeted ads. i tried reversing the firmware but it was aes encrypted and no keys unless tear it apart and do uart/jtag magic. zero days it is. root shell on new samsung TVs! discovered PRIVACY HORROR. write up?
347
3,287
350
22,555
1,564,520
Thomas Findlay retweeted
We benchmarked 17 open OCR models on OmniParseBench, our new OCR benchmark that builds on AllenAI's olmOCR-bench.
22
31
1
322
14,494
Thomas Findlay retweeted
TanStack AI 1.0 is officially stable! 🎉 Build chat, voice, image generation, agents, and harnesses into your apps, with your choice of models, UI framework, and infrastructure. Your AI, your way. tanstack.com/ai
83
122
36
1,490
97,979
Thomas Findlay retweeted
emulate v0.12.3 - AWS Cognito: User & Identity Pools, signed tokens, local OAuth, SDK support - Slack: Interactive buttons, modals, signed callbacks, event retries, Slack Connect, lifecycle simulation - SQS: JSON protocol support for modern AWS SDKs - Google OAuth: Optional token & scope validation - Resend: Recipient restrictions, persisted send attempts - Vercel Blob: Upload, listing, delete and multipart fixes - GitHub: Check-run pagination, App identity fixes github.com/vercel-labs/emula…
4
13
2
176
9,608
Thomas Findlay retweeted
As a builder in the AI video space, I was terrified about how much markup API providers charge for simply routing the models. Higgsfield API adds a 40% markup even with its maximum advertised discount. Fal adds 100%. Runway adds 414% (Seedance 2 480p) I might be hated by the industry, but : 
 Today, we’re launching Sume API, the first image & video model provider with 0% markup. For example with Seedance 2.5 1080p • 50% cheaper than fal • 50% cheaper than higgsfield api (29% even with biggest discount) • 28.02% cheaper than kie ai The routing infrastructure layer is never the moat. We believe that APIs should be commoditized, and the moats will be built at the application layer. Check the pricing comparisons below, and see how the broken industry is saved.
466
393
155
5,767
874,911
Thomas Findlay retweeted
How do you _guarantee_ your agent's code is correct? You prove it. Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch. PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team. PDD Kit takes an app's login flow from intent to a verified pull request: It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust. Once you approve the spec, the Verus verifier automatically proves the code meets it. Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs). It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible. The goal is a verified software factory, where engineers review specifications instead of code. Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
87
136
78
2,058
400,143
Thomas Findlay retweeted
At T3 Code, we take regressions like this seriously. I just introduced a "noEmDashCopy" lint rule to prevent this going forward 🫡
btw, em dash detected. you will hate this and need to fix this @theo
52
9
7
1,181
97,569
Thomas Findlay retweeted
I made a skill that generates your marketing images — on brand, every size. OG images, X cards, blog heroes, newsletter headers — AI-generated, held to your palette and type, and wired into the publish pipeline so every post ships with its set. npx skills add coreyhaines31/marketingskills
8
3
66
5,647
Thomas Findlay retweeted
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to. Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code. Here's what that means for you:
302
421
258
8,735
1,021,856