Listen, build, ship, repeat.

Joined January 2021
Prompt: This is a blank project. I want you to make an in browser game based on the Tesla Roadster event from yesterday. I want the in game car to meet all of the specs that the actual car can. I think an interactive car driving simulator where I can drive the car through the same demos that they gave at the event yesterday would be best. I want this to be as well optimized for browsers as it could be so use WebGPU where needed and make it the best quality browser game possible, and make it run at at least 30 fps, but probably more. Ask me questions as needed, or just take off and start going. Time: 54 minutes Model: Opus 5.5 (high) Harness: T3 Code Result: roadster.ethanglenn.dev
61
Well, a weird bug in Claude Code got me to try out T3 Code. It's way better than I thought. Lives up to all the hype online.
2
2
81
Claude Max 5x feels unlimited with Opus 5.5. I have yet to hit a 5h limit or my weekly.
52
I think this is super cool and something I will use, but how long until sites start blocking mail.grokbot.com email addresses?
Grok Bot now has its own email. Bot can use it to sign up for services, contact businesses for you, or schedule time with someone.
1
21
Update: Still no Sonnet 5.5 access on bedrock.
Anyone at @awscloud @awsdevelopers that can help me get access to Sonnet 5.5 on bedrock?
56
Claude seems to be ignoring the global settings.json. I turned off the attribution section, but it's still been adding it. @ClaudeDevs @lydiahallie
18
Ethan Glenn retweeted
The most important coding skill: read. Teach yourself how to read. Read the agent output. Read the blog post. Read the paper. Read the code (if it applies to you). Don't summarize.
243
605
94
6,968
173,145
Ethan Glenn retweeted
Important note regarding Grok @Bot: Going forward, @SpaceX will use the best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno and other leading APIs. Whatever is most likely to give you the best outcome.
7,482
7,654
3,700
107,702
79,733,606
Update: Talked to a sales rep and it's going to take 2 weeks to get me Sonnet 5 or 5.5 on @awscloud . I was able to enable the model on @googlecloud in about 5 minutes. Now I contemplating moving the entire stack to GCP or wait two weeks to get model access through AWS.
Anyone at @awscloud @awsdevelopers that can help me get access to Sonnet 5.5 on bedrock?
45
Anyone at @awscloud @awsdevelopers that can help me get access to Sonnet 5.5 on bedrock?
1
1
181
The worst kind of AI haters are the ones that talk about the latest models like they’re the same as last year’s Sonnet 4.5 or GPT 5.
1
35
`/code-review high` runs so much faster with Opus 5.5! It's review is also much higher quality.
1
1
31
The new golden rule of AI
my rule for sharing Claude output (PRs, artifacts, messages) is that I only do it if I would be happy sharing the prompts
27
Switched to iPhone and notifications are weird. I oddly find myself missing a lot more notifications than I did on Pixel.
13
Opus 5.5 is the best model I've used in a while.
1
4
128
Introducing Googlebook, a new category of laptop, available for preorder today. 💪 Crafted with 2.8K OLED touchscreen displays, 14 hour battery life and all the performance needed to power your ideas 📳 Engineered to sync effortlessly with your @Android phone, so you can jump between your phone and laptop without skipping a beat ✨ Designed for Gemini Intelligence, with personalized, proactive help when and where you need it
1
259
Best news I've heard all week!
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.
7
Ethan Glenn retweeted
no man i think it's really cool to install random binaries on my computer with no sandboxing in order to make an api call
15
10
5
446
41,013
Ethan Glenn retweeted
Dario is right
We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training. You can read the full post here: darioamodei.com/post/we-must…
6,284
6,400
2,349
57,923
12,639,422
I think I'm slowly becoming Grok @bot pilled. It's come in hand a lot over the last few days with working on the go.
24