Building apps, messing with local AI, gaming and Dodgers! Creator of Lofi Years. 🔊
Orange County, California
Joined January 2009
- Tweets2.9K
- Following432
- Followers1.9K
- Likes23.1K
Pinned Tweet
Holy shit… I just launched my first iOS app! 🤯
Lofi Years is officially on the App Store. From an idea to an app you can actually download. Still wrapping my head around that.
Give it a spin and let me know what you think 🤘🏻🎧
apps.apple.com/us/app/lofi-y…
Codex reset just happened (thanks Tibo), I am using Sol 6.1 on medium and 2% usage has already been eaten up. 😅
Tommy Ferris retweeted
We had a security breach last night related to a large scale distillation attack that impacted 1.4% of OpenCode Console users
We have notified them all this morning via email. If you did not get an email you were not impacted, it was a subset of users who had external providers linked
The incident is ongoing so we cannot share more details at this point but we are working with Anthropic, OpenAI, and Google to remediate
It’s been one hell of a day with the evacuations here in San Juan Capistrano due to the Norte Fire. OC fire has been holding it down. 🙏🏻🔥 #nortefire #sanjuancapistrano
I’ve been testing GLM-5.3-Flash Free in OpenCode on one of my projects, and it’s terrible. All hype.
Hit my Claude session limit, waited for the reset, then opened it about 30 minutes later… already at 47% and I haven’t even done anything yet. Lol wtf? 😂
selected model is at capacity. please try a different model.
selected model is at capacity. please try a different model.
Tommy Ferris retweeted
now you can run local ai on a $200 gpu
rtx 20 owners, you're in. one line now runs local ai on every rtx from the 20 series to the 50 series and amd radeon with 8gb or more, sm75 to sm120, windows or linux
> windows, paste in powershell:
irm raw.githubusercontent.com/su… | iex
> linux, paste in terminal:
curl -fsSL raw.githubusercontent.com/su… | bash
what your vram gets you
> 8gb, chat, up to 64k context, 52.6 tok/s on an rtx 2070 super, about $200 used
> 12gb, agentic coding, 131k context, 50.1 tok/s on an rtx 3060 12gb
> 16gb and up, vision, the full 262k, 67.3 tok/s on an rtx 5060 ti 16gb
rtx 20 on windows and radeon are still in beta, run the speed check once and reply with your line, every card that posts becomes a row for the next owner
every 8gb to 16gb gpu owner on this planet, rejoice✨. you can run local ai now with one line, linux or windows, nvidia or amd, all welcome
it works on nvidia rtx 30, 40, 50 and amd radeon rx 6000, 7000, 9000, any card with 8gb or more
> windows, paste in powershell:
irm raw.githubusercontent.com/su… | iex
> linux, paste in terminal:
curl -fsSL raw.githubusercontent.com/su… | bash
it finds your card, downloads about 8gb one time, and gives you a chat page in your browser
on my rtx 3060 12gb it writes up to 50 tok/s, faster than you can read, and keeps 131K tokens in mind at once, about a whole book
what your card keeps in mind
> nvidia 8gb, 98K, or 64K if it also runs your screen
> nvidia 12gb, 131K
> nvidia 16gb and up, 262K
> amd 8gb, up to 64K
> amd 12gb, about 195K
> amd 16gb and up, 262K
run it, then post your card and your speed here, your numbers show the next person with the same card what to expect
I am doing some dev work in Grok 4.7 build today, so far its doing really well. Not sure why I didnt give it a try sooner.
I have a Starlink mini in my Cybertruck, but I am surprised Tesla does not provide a Wi-Fi hotspot when you subscribe to their premium subscription.
