Solving the hardest problems I can get my hands on 🚀 Co-Founder & CTO @withmantle Formerly: Pivotal, VMware, Xtreme Labs
Toronto, Ontario
Joined March 2010
- Tweets7.1K
- Following579
- Followers1.1K
- Likes5.6K
dappwright just got 3.5× faster.
Same @MetaMask script, same machine:
2.13.14: 62.8s
2.13.16: 17.8s
Fixed sleeps are gone. It now waits on what the wallet actually does, reduced motion, and an early popup no longer hangs an action.
github.com/TenKeyLabs/dappwr…
Plugins: 80+ internal plugins implement the 2.0 features, TUI plugins are now stable, and plugins hot-reload mid-session.
The catch is that it's a breaking release: 1.0 plugins won't work, the server API is different, and the SDK is still changing. Full notes: anoma.ly/notes/opencode-2-0/
The AWE Benchmark tables are easier to read now:
• Column headers stay pinned as you scroll down a table
• Model names stay pinned as you scroll a wide table sideways
• The page caps at a readable width, so names line up with their scores
research.withmantle.com/awe
Me: claude, make the tests faster.
Claude: done.
Me: why do they seem slower?
Claude: my comparison script had a bug: it read "152ms" as 152 seconds. 👀
Just when you think you can put down your benchmark harness…
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!
I added Cloudflare’s Claric to our AWE benchmark, and it finished near the bottom, which is what I expected and not really the point.
Falls short:
- four sections (called by year, rows, highlights and sourcing channels) came in at 0%
- table-heavy financial statements sat at 69%
The spread is the interesting part. A fast single-pass model that nails some sections and misses others could work as a first pass, or as a gate that routes the hard sections to a reasoning model. See the full results at research.withmantle.com/awe
Looks like @GoogleCloud has quietly beta released SSH access to Cloud Run containers. Much appreciated for those quick debugging sessions. 👏 docs.cloud.google.com/run/do…
yes plz 🤩
A single command to install @omarchy on your iPad
Coming soon
Video is sped up, total install took 3.8 minutes
@OmarchyMac @OmarchyUpdates @dhh @OmarchyLinux @tcballard