fly³ retweeted
I feel like I haven't said this enough lately, or even at all, and I need to say it.
Opus 4.8 is a good model, and Claude Code is a very solid harness. What @bcherny and team are doing is exceptional, and nobody should be sleeping on this combo.
While I do talk about Codex and GPT 5.5, which has been my daily driver for the last couple of months, that doesn't mean I don't like Claude Code and Opus 4.8.
I use both. For whatever reason I just tweet about Codex a lot more, and that's probably because I like their Desktop app a lot, this is probably the biggest gap rn between the two.
Claude Code is very comparable to Codex when you compare CLI to CLI, but app to app, Codex is significantly better than Claude Code in the Claude app. This is where @thsottiaux and team have really shown some serious innovation and focus.
But I'm hearing people diss Opus 4.8 way too much lately. It is a very good model, and while I do like GPT 5.5 more, that doesn't mean 4.8 is bad.
Still have plenty of love for you Anthropic 🫶
fly³ retweeted
We never had more npm downloads than this week on @openclaw - comined with Docker, GitHub, company-internal deployments and the numerous forks, real number is more in the 10-20 million downloads/week.
fly³ retweeted
You can now use your @grok or X Premium subscription in @opencode.
Use the model powering Grok Build for high speed and codebase intelligence.
x.ai/news/grok-opencode
fly³ retweeted
OpenAI frontier models and Codex are now generally available on AWS, giving enterprises a new way to build on Amazon Bedrock with OpenAI through the security, compliance, and governance workflows they already use.
This is also the beginning of a broader expansion of OpenAI capabilities on AWS, including future availability for cybersecurity capabilities like Daybreak.
openai.com/index/openai-fron…
fly³ retweeted
I'm running a gazillion codex and 100s of vms.
Only way i can work now, each tmux pane is another tmux to a remote m4 mac mini via mosh with 6x4.
Then each one of those codex sessions is farming out all its testing on mac, windows, docker on AWS and Azure spot instances via crabbox.
fly³ retweeted
I want to share some unglamorous work I’m proud of.
Starting in late March and landing around the Apr 7 OpenClaw release, we intentionally cut aggregate OpenRouter token usage by ~35%, down to ~400B tokens.
This wasn’t one trick. It was good engineering across paths agents hit all day: oversized tool results, compaction/overflow recovery, background and subagent context, and prompt caching.
My part was mostly the tool-result / overflow path. Vincent worked on cache boundaries and fingerprints. Boris fixed deterministic tool ordering and cache-preserving compaction. Ayaan helped with subagent light context and nearby context-shaping fixes.
Relevant commits in reply.
fly³ retweeted
what pushed us to finally implement it is heavier use of worktrees
now that i have sessions going across different worktrees very annoying to find them and open my editor in the right spot
we'll ship the worktree feature out from the flag next week
fly³ retweeted
imagine a benchmark of two editors
one opens a file 10x faster! wow it must be better. but oh wait they just disabled syntax highlighting
real products have to do things that make it worse on benchmarks but better in practice
fly³ retweeted
Claude has a cheat code!
Anthropic just dropped a free 33-page playbook that most people will never find.
It reveals a hidden feature called the “Skills” folder.
Build it once. Never explain your process again.
Here’s how to get it 👇🏽👇🏽👇🏽
fly³ retweeted
You’ll also get a skill file that you can use with coding agents like Codex and Claude Code.
It can review your animations, suggest improvements, and basically answer all your motion-related questions based on my experience gathered over the years.
Here’s a quick demo:
fly³ retweeted
OpenClaw folks will be at the Open Source Zone on the conference floor, @steipete also has a session on Tuesday, and we're hosting an OpenClaw event with @github on the evening of the 3rd! luma.com/OpenClaw-GitHub
I'm building a web app to share my location while on the ground. Will share via my Twitter over the weekend.
fly³ retweeted
Every time someone says "Claude's limits are too restrictive," I immediately know how they're using it.
Most people treat Claude like a chatbot.
Power users treat it like a system.
Same free plan.
Completely different results.
The difference is usually:
→ Better context management
→ Shorter prompts
→ Smarter session resets
→ Claude Code workflows
→ Knowing when not to waste tokens
I turned the highest-leverage tactics into a simple infographic:
15 ways to get dramatically more value from Claude without paying a cent more.
Save this before your next "usage limit reached" message.
fly³ retweeted
ICYMI 👀: Claude Code CLI can now operate Claude Platform, including the Messages API and Claude Managed Agents.
One CLI to rule them all 🤖
fly³ retweeted
Codex is now insane for internal tools.
Any app you want, hosted with new Codex sites feature
& Convex just released a plugin today so you can easily add db....
Very fast and easy to use.
Clean "Sites" tab shows all the sites you're building.
However, you can't make the sites public (yet)
