←
Patricio6,093 posts
Patricio avatar

Patricio

@PatricioOnCode

Dev Advocate @orca_build 🐋 orca.dev Building with AI. Finding better ways to do it. Showing them on video. youtube.com/@Orca-SI

◷ Joined June 2011▧ 580 Photos and videos
Wes Grimes avatar
⟳ Patricio retweeted
Wes Grimes@ncfrontiersman·Oct 28

🎉 WayShare 0.3.0 released! It adds full RDP support. Your Hyprland desktop now works with Windows App on iPhone, iPad and Mac, Windows Remote Desktop, and FreeRDP, alongside Mac Screen Sharing. Same login for all of them. On iPhone it even resizes when you rotate. github.com/wesleygrimes/ways…

0:14
Patricio avatar
Patricio@PatricioOnCode·Oct 27

Missed opportunity: --run-with-scissors

Fun fact: `--dangerously-skip-permissions` doesn't actually approve EVERYTHING—we still block some obvious things like `rm -rf ~`. But today's release will let you disable this if you really want, by setting a new env var `CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS=1`

Orca avatar
⟳ Patricio retweeted
Orca@orca_build·Oct 26

🚨 Heads up: Anthropic has a metering bug where Agent SDK chat UIs burn your Claude Code 5h limit ~1.7x faster than the TUI. Orca has first-class support for both chat UI and the real TUI. right-click → move your live session into the Claude Code TUI, full context. Pretty UI when you want it. TUI when limits matter.

1:56
Patricio avatar
Patricio@PatricioOnCode·Oct 26

Can’t wait for the extension 😍

Just found out (from an insider) why Google is so behind: Politics For example, anti-gravity can't make any change on how it controls Chrome. And remember what happened to the guy who made the gSuite CLI 🔫 Meanwhile @orca_build is shipping Chrome extension support this week

Patricio avatar
Patricio@PatricioOnCode·Oct 24

TIL

Every Mac on macOS 27 now has a free LLM built into the Terminal. No account. No API key. No internet. No token bill. Setup (1 minute): 1. sudo fm license (enter your Mac password, one time) 2. fm available (checks the model is downloaded) 3. fm respond “your question” Works on any Apple Silicon Mac, M1 included. - Pipe files: cat notes.txt | fm respond -i “summarize this” - Get JSON back: build a schema with fm schema object, pass it with --schema - Local API: fm serve gives you an OpenAI-compatible endpoint on localhost - Resume chats: sessions save to ~/.fm/sessions/ The limit is 4,096 tokens per session, and your prompt, instructions, and the answer all share it. So skip code and math. Use it for summarizing, extracting, classifying, and rewriting. Free, private, offline, and already on your Mac.

Post attachment
Povilas Korop | AI Coding & Laravel Educator avatar
⟳ Patricio retweeted
Povilas Korop | AI Coding & Laravel Educator@PovilasKorop·Oct 24

I see a trend of indie hackers creating cheaper versions of popular SaaS products. But with all AI power we have, wouldn't it be better to focus on creating BETTER products instead of cheaper? Look at what frustrates you in software and maybe try to build a better version?

Jinjing Liang avatar
⟳ Patricio retweeted
Jinjing Liang@JinjingLiang·Oct 20

Don't understand why all other chat ui just attach images as a separate array as opposed to making them part of the text input. It definitely hurts AI accuracy. So we make sure to not do that in Orca.

Orca’s Chat UI now preserves image positions in your message, just like terminal agents. Many of our users switch between Chat UI and terminal view all the time. We want both to perform equally well: same first-party agent harness underneath, same context going in.

0:11