Dwayne Forde
banner
dwayne.io
Dwayne Forde
@dwayne.io
Solving the hardest problems I can get my hands on ๐Ÿš€
Co-Founder & CTO @withmantle.com
Formerly: Pivotal, VMware, Xtreme Labs
There are a lot of tasks that AI isn't suited for, but there are a ton of tasks where it augments and greatly accelerates workflows.

Any tool can be used in a right and wrong way. I think the world is still figuring this one out.
January 8, 2026 at 4:06 PM
Agreed. You need to own and secure the entire stack(s) to a solution to really accomplish true E2EE.
January 8, 2026 at 4:01 PM
Beyond all of this, @metamask.io is looking better than ever. Always like seeing all the easier ways folks can onboard into the ecosystem.
December 26, 2025 at 8:58 PM
Doing requires an environment flag (PW_CHROMIUM_ATTACH_TO_OTHER = '1') to be set before the context is created. Since dAppwright creates its own context, this is easy for us to do at runtime without introducing a breaking change for burdening users with this context.
December 26, 2025 at 8:58 PM
Waiting for this flexibility also meant that we got introduced to the new side panel UI that MetaMask has incorporated. Playwright doesn't really consider the side panel to be part of it's official supported mechanisms but you can dig the page out of the browser context.
December 26, 2025 at 8:58 PM
Specifically waited for 13.12.x where there is more flexibility when setting up the wallet to turn off backup & sync. Without this option disabled, there would have to be 3-5min waits for the list of accounts to sync since the test wallet has > 200 accounts.
December 26, 2025 at 8:58 PM
dAppwright v2.13.0 released with @metamask.io 13 support. ๐Ÿš€

Delayed support was due to being able to control the backup and sync functionality which really slowed everything down at scale, and to adopt support for the new sidepanel ui.

github.com/TenKeyLabs/d...
December 26, 2025 at 5:45 AM
This is just the start, there are a lot of other data points at play when it comes to picking models that will be added over time.

Hope it helps you too. Feedback always welcome!
December 23, 2025 at 11:00 PM
Lots of folks have always asked for a copy of my spreadsheet, this will auto-update and be more sustainable to keep everyone in the loop. All data is stored in the browser, nothing leaves your machine.
December 23, 2025 at 11:00 PM
At @withmantle.com, weโ€™re constantly testing different models for different tasks. Performance matters, but so does cost when youโ€™re shipping at scale.
December 23, 2025 at 11:00 PM
For years, I've had a spreadsheet that consolidates current pricing for major models to track and compare the cost of different AI workflows across the company.
December 23, 2025 at 11:00 PM
In the last couple of weeks, 3 new models dropped and I caught myself scrambling to keep up with the latest pricing.
December 23, 2025 at 11:00 PM
I've launched a new tool for planning your cost for AI workloads (llm-calculator.withmantle.com). Why? ๐Ÿงต
Mantle | LLM Pricing Calculator
Compare LLM pricing across providers like OpenAI, Anthropic, Google, and more. Calculate costs for different models and scenarios.
llm-calculator.withmantle.com
December 23, 2025 at 11:00 PM
Reposted by Dwayne Forde
The Mantle Office Tour (Holiday Edition) just dropped ๐ŸŽ„

This edition features champagne sabering, budget gifts, and our head chef, Ivan Chen, sharing his hot take on whether mulled wine qualifies as soup.

Happy holidays from the Mantle team! ๐Ÿฅ‚

youtu.be/Qmh6zjJi0-g
Mantle Office Tour (Part 4) | Holiday Edition
YouTube video by Mantle
youtu.be
December 23, 2025 at 2:03 PM
"Victory is claimed by all, failure to one alone." -Tacitus
December 17, 2025 at 10:50 PM
yes
December 16, 2025 at 6:11 AM
December 13, 2025 at 1:17 PM
@google created a benchmark to show off their categorization and extraction strengths ๐Ÿ‘€ deepmind.google/blog/facts-b...
FACTS Benchmark Suite: a new way to systematically evaluate LLMs factuality
The FACTS Benchmark Suite provides a systematic evaluation of Large Language Models (LLMs) factuality across three areas: Parametric, Search, and Multimodal reasoning.
deepmind.google
December 13, 2025 at 1:17 PM
It was great event. Thanks for organizing!
December 13, 2025 at 12:55 AM
Congrats! Excited to hear what the next thing is. ๐ŸŽ‰
December 13, 2025 at 12:47 AM
Where has this been all my life! ๐Ÿ™Œ
December 13, 2025 at 12:45 AM
Couple of new versions of github.com/TenKeyLabs/d... released today. ๐ŸŽ‰
- A bit better at grabbing older github releases
- Metamask bumped to latest v12
- New updateRpc method
GitHub - TenKeyLabs/dappwright: ๐ŸŒ๐Ÿผโ€E2E testing for dApps using Playwright + MetaMask & Coinbase Wallet
๐ŸŒ๐Ÿผโ€E2E testing for dApps using Playwright + MetaMask & Coinbase Wallet - TenKeyLabs/dappwright
github.com
December 11, 2025 at 2:03 AM
Reposted by Dwayne Forde
โ€œRaise just enough money so you feel like youโ€™re under pressure.โ€

That was Steven Trieu's (CFO of 8090 Solutions/Social Capital) advice when we asked how founders should think about fundraising.

Steveโ€™s framework is simple: Raise enough oxygen to reach your next meaningful milestone, but no more.
November 24, 2025 at 2:07 PM
Another IDE from @developers.google.com. Interesting premise to push the Agentic AI workflow to its limits. We'll see if this one sticks. ๐Ÿ™Œ antigravity.google/product
Google Antigravity
Google Antigravity - Build the new way
antigravity.google
November 23, 2025 at 3:20 PM
Donโ€™t worry, AI will fix it. ๐Ÿ‘€
November 5, 2025 at 2:03 AM