Joined December 2017
5 Photos and videos
Barrett Woodside retweeted
Claude Status Page vs Whole Foods Three Pepper Blend Who wore it better?
122
492
9,674
407,719
eSIMs are great and all, I really enjoy using Ubiji and/or Saily when I travel. However, if you get your iPhone repaired and they swap the mainboard (my Lightning port stopped working), then you need to bring another device to the Apple store to re-activate. Also, turn off account security temporarily with your cell carrier. In sum: 1. Bring a charger and charge cable to prove to the Apple store employee that the phone no longer charges 2. Turn off account migration/SIM swap security 3. Bring a second device (laptop, iPad, etc.) that's already logged into your iCloud 4. Hope for the best (like your partner on your cell plan is still in cell service and can be your second factor, if need be) While I could restore from iCloud backup (I normally use a cable to back up my phone when I upgrade, but couldn't do that with a busted port, nor would Wi-Fi backup work without a port connection first), I was then prompted to do a 30-minute iOS upgrade (no way to bypass). So restoring your phone after a repair, is a massive time waste with eSIMs, unless you do your homework and thoroughly prepare in advance.
1
2
277
OK, even if you prepare, most carriers still fail. Here's the rundown: 1. @ATT's transfer eSIM flow is broken because it requires 2FA from the phone that was repaired (via a recycled mainboard) 2. @Google_fi only lets you transfer one line and the one I wanted to move over was the secondary. I had to cancel it 3. @Visible's eSIM transfer mostly worked as intended, except I was totally logged out on the restored-from-backup device, so it prompted me to start new service rather than restore from backup. Luckily I could use e-mail as a second factor
2
223
Barrett Woodside retweeted
3 Apr 2025
Replying to @JeffDean
Are you ReLU sure that's the best way to calculate it? Sounds taxing!
3
9
203
17,660
Fun generative video clips with @krea_ai, courtesy of @ErwannMillon and team. First pass, but should make for some fun projection mapping tomorrow night with @welovesfofficial!
10
766
Barrett Woodside retweeted
10 Oct 2024
Quantization update! Transformers is now compatible with models quantized with llm-compressor library from @vllm_project or models in compressed-tensors format. This means that you can also enjoy high quality quantized models from the @neuralmagic team!
2
16
64
4,844
I'm so grateful for all the hard work from @trsohmers and our excellent team at @positron_ai, including the FPGA team in Liberty Lake, WA, and an amazing software team distributed across the entire country!
Positron is proud to share our latest inference performance versus the GPU-based competition: ✅ 70% faster token generation on Llama3.1-8B ✅ 1/3 power usage on Llama3.1-8B ✅ 51% cost savings versus DGX-H100 💸 (Yes, IYKYK: less than half the cost.)
2
4
368
PSA: If you're looking for properly quantized LLMs, huggingface.co/nm-testing (NeuralMagic, creator of Marlin) is the new Tom Jobbins huggingface.co/TheBloke By that I mean you'll find recent models to easily run with @vllm_project, text-generation-webui, or @OpenWebUI
229
Barrett Woodside retweeted
#GPT4V is magical…A machine that can textually explain an image representing its own operation, and then suggest a new way to visually represent itself. What a time to be alive.
3
12
62
33,824
Although I'm 6 months late to the #fsdbeta party, I have two brand new cold weather issues with my @Tesla Model 3: 🧵1/3
2
4
597
2. Windshield wipers can't be disabled while on FSD, which means sometimes they automatically activate, only to rub white road gunk into my windshield, blocking the front-facing cameras. 🧵 3/3
1
4
424
I know these may seem minor compared to getting to use the best L2 system on the market, but...please hjälp?!
2
267
🧵1/2 Today I realized that @Microsoft is the ant...
1
4
390
🧵2/2 ...and @OpenAI is the mushroom (ophiocordyceps unliateralis) growing out of that ant's head. CC: @tszzl
1
5
344
Barrett Woodside retweeted
5 Apr 2023
I just wrote a blog post on how we used mmap() to make LLaMA load faster, run in parallel, and use less memory. In this post you'll find all the facts. justine.lol/mmap/
17
228
1,366
185,416
Barrett Woodside retweeted
Announcing that Lambda has raised $44M to build the best cloud for training AI. (Lots of GPUs.) youtube.com/watch?v=zsfd-GHI… I'll be doing a Q&A on Twitter for the next hour. Just reply in this thread.

35
44
382
86,318
Barrett Woodside retweeted
30 Jan 2023

19
82
715
103,660
Proud to be working on this! Should be a really fun Saturday. Come hack with all the large and foundation and generative models.
We're hosting a Generative AI & LLM hackathon at @scale_AI HQ in SF on 1/21. There will be: 🏆 prizes (Napa tour, skydiving, drones) 🏤 workshops (Advanced Prompt Engineering with @goodside) 🧑‍⚖️ judges like @karpathy Application link below—come build something cool❗️
12
3,487
Barrett Woodside retweeted
16 Dec 2022
✨ Calling all AI executives and professionals! ✨ We’re looking for your feedback on how AI will impact your business in 2023! Help us by completing a short survey. Your contribution will be used in our upcoming report, coming in early 2023! scl.ai/3iYoTOH
3
3
8
4,312