Christian | AI | 21 @offlinebase
- Tweets 2,342
- Following 2,966
- Followers 416
- Likes 5,298
Thanks @datadoghq for your startup program. We (myself and @Electricaliee ) are getting our jetson orin nanos onto our dashboard now and discovering a ton of potential optimizations for @offlinebase
2
3
72
When are there going to be price/duration pricing for LLMs?
Mercury 3 is running at 1000 tok/s
$0.70 per million output
16.667 min to one million output tokens (uninterrupted token streaming)
Vs
Haiku 5.5 runs at 232 tok/s (according to @ArtificialAnlys)
$0.50 per million output tokens
~72 min to one million output tokens
So you’re [let’s call it] investing your $ into tokens, 5x faster (omitting price).
Of course, this isn’t a big deal because you would ideally get to your outcome faster and still spend the same amount of tokens (if not less because Mercury 3 is reportedly smarter than Haiku 5.5).
1
1
1
50
Working on using @liquidai d1 to help you moderate your, your kids, your employees, etc. before things get sent to AI models, infra, etc.
All done locally!
Working on this and more @offlinebase
1
1
5
251
@alexandr_wang @elonmusk @sama I think every personal agent should have a locally running moderation model on the consumer’s device that blocks specific things from going to your guys’ infra to protect both the consumer and protect yall from liability!
11
Embedding Gemma 2 routing you between Gemini 4 Argon and Gemma 4 e2b.
Check it out.
Thanks for the insane release(s) @OfficialLoganK @Google @GoogleAI @sundarpichai @GlennCameronjr @googlegemma @GeminiApp @GoogleAIStudio @Electricaliee
@GoogleLabs (let's make this an official experiment!)
Check out GemmaGemini[.]com
3
2
5
580
@anderdobo @IanBallantyne hey! By any chance, do you have any say in who gets admitted to agihouse.org/events/the-goog…
24
Was blessed to win the latino x AI hackathon last week at Columbia Business school
w @GilFoss and my boy Felix
61
I wonder if there is any demand for data center and edge compute live streams?
It would be cool to hear the data center whirr as you send a prompt, also to get more transparency
I think I may set up a live stream for my jetson orin nanos and raspberry pis that are running models
2
59
Actual “decision tree”.
@Raspberry_Pi 5 running @liquidai d1 600m
Being powered by solar
With a diy tree connected to
Figuring out how to productize this for < $125
2
4
20
4,335
I have d1 600m from @liquidai running on a @Raspberry_Pi 5 (2gb ram) powered by a solar panel in my apt.
1
11
113
Congrats on Beam, @zkwentz and the @reflection_ai team!
Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.
- Frontier reasoning efficiency
- Advances the Western open frontier on coding & agentic tasks
- Trained end-to-end from scratch
Full weights release this month.
Learn more about Beam: reflection.ai/beam
1
3
115
Had a good time going to the Open by Design event hosted by @reflection_ai @nvidiaai @togethercompute with @electricaliee
If you’re interested in local, edge, open source ai, let’s chat!
2
2
8
252
Ethan retweeted
Try out @liquidai new LFM 2.5 24B model routed by their D1 decision model, made by us @offlinebase. Website in comments.
@EthanCastr
1
2
2
64
Insane!
Today we’re releasing Muse Spark Open, the most capable US open-weight model to date.
Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning.
Key Model Specs:
→ 816B total / 42B active parameters
→ 1M token context window
→ Natively multimodal across text, image, video, audio
4
152