JonSaadFalcon Profile Banner
Jon Saad-Falcon Profile
Jon Saad-Falcon

@JonSaadFalcon

Followers
1K
Following
604
Media
26
Statuses
233

AI PhD @hazyresearch @StanfordAILab @stanfordnlp Previously @databricks @allen_ai @GeorgiaTech

Palo Alto, CA
Joined January 2021
Don't wanna be here? Send us removal request.
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
42
124
378
@shishirpatil_
Shishir Patil
18 hours
I bet in 2022 that large LMs would end up on the edge — not for privacy (most don't care), but because on-device inference feels free, while the cloud always feels metered. Although less efficient, the cost comes out of the user’s phone battery (practically free and diffused).
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
0
1
12
@JayaGup10
Jaya Gupta
1 day
AI has given venture capital a new way to repeat an old mistake: kingmaking. The pattern from 2021 is back: a category becomes "obvious," a top-tier firm anoints its winner, and everyone else acts like the decision is final. Sierra for support. Harvey for legal. Applied Compute
35
40
499
@simran_s_arora
Simran Arora
3 days
AI has been built on one vendor’s stack for too long. AMD’s GPUs now offer state-of-the-art peak compute and memory bandwidth — but the lack of mature software / the “CUDA moat” keeps that power locked away. Time to break it and ride into our multi-silicon future. 🌊 It's been a
12
98
564
@IBMResearch
IBM Research
1 day
This week, @StanfordAILab shared findings showing AI is entering a new era: from large models in the cloud to smaller, efficient ones running locally. In tests with IBM Granite 4.0, compact models handled 88.7% of queries, cutting energy and latency. ➡️ https://t.co/yGbvuG0BIo
2
16
71
@jdunnmon
Jared Dunnmon
2 days
This is exactly the type of systems-level thinking we need to get as much AI bang as we can for our electron buck. As China continues to outpace the US in energy deployment, capitalizing on such efficiencies will become increasingly important to continued US AI leadership.
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
2
2
3
@lmsysorg
LMSYS Org
2 days
Totally. SGLang's design choices directly improve IPW: 1. RadixAttention for KV cache reuse 2. Fast structured generation 3. Optimized scheduling Every efficiency gain = more intelligence per watt = more AI running locally
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
0
2
14
@kimmonismus
Chubby♨️
2 days
A very important and incredibly exciting research project: Intelligence Per Watt: A Study of Local Intelligence Efficiency Local AI models are getting dramatically more efficient, and the Hazy Research team proposes Intelligence-per-Watt (IPW) as the key metric to measure how
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
14
9
158
@awnihannun
Awni Hannun
2 days
Local AI, measured by intelligence-per-watt (IPW), improved 5.3× in just 2 years! And it feels like the slope is still quite steep. Imagine another 5-10x in the next 2 years. Exciting.
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
8
11
129
@rohanpaul_ai
Rohan Paul
2 days
Great theory proposed in this paper Intelligence per watt (IPW): intelligence delivered (capabilities) per unit of power consumed (efficiency). The paper asks how much work local AI on laptops can take over from cloud systems. Argues local AI can handle most queries, and
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
10
11
46
@Azaliamirh
Azalia Mirhoseini
2 days
Introducing intelligence per watt, and predicting a distribution shift from cloud to edge inference!
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
3
9
67
@Azaliamirh
Azalia Mirhoseini
2 days
A shift from cloud to edge? We took a closer look at “Local LMs” (≤20B active parameters) and found that they are: - Surprisingly capable, with 3.1× improvement since 2023 - Increasingly efficient, with 5.3x improvement since 2023 This suggests a shift from mainframe inference
4
17
76
@_akhaliq
AK
2 days
Intelligence per Watt Measuring Intelligence Efficiency of Local AI
5
9
67
@exnx
Eric Nguyen
2 days
Intelligence per watt (IPW) is a really clean and simple framing. Great way to push this metric forward Really cool work by @HazyResearch
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
2
1
25
@BaigYasa
Yasa Baig
2 days
@JonSaadFalcon and @Avanika15 strike again! IPW has the potential to be THE rallying cry for MLSys in the same way PPL was for the NLP community. Really great work and a great read!
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
1
1
3
@ash_locked
Aishwarya Mahesh
2 days
the kind of work that bridges ai research and energy systems!
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
1
1
7
@talaei_shayan
Shayan Talaei
2 days
While scaling compute might enable smarter models, it’s equally important to ensure everyday intelligence remains practical and accessible. IPW defines a tangible metric to measure progress toward smarter and more efficient models. Great work @jonSaadFalcon @Avanika15!
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
0
1
7
@wesgriffin07
Wes Griffin
2 days
Intelligence per watt: the metric that matters for getting AI out of data centers and into every device. Absolute privilege working on this with @Avanika15 and @JonSaadFalcon
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
5
1
13
@gpusteve
steve
2 days
our manifesto (maximizing intelligence per watt):
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
0
2
10
@simonguozirui
Simon Guo
2 days
Intelligence per watt (🧠/⚡️) is such a cool metric to capture the trend shifting intelligence from cloud to local! Kudos to @JonSaadFalcon @Avanika15 and team for uncovering this insight, after many many hours of profiling on so many workloads, models, and hardware.
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
1
3
19
@UrmishThakker
Urmish Thakker
2 days
Great work by @JonSaadFalcon @Avanika15 @Azaliamirh @etash_guha and others at @HazyResearch ! Power is one of the biggest constraints to adding more compute for AI! Glad to see they have validated what we have been saying at @SambaNovaAI for awhile. We are the most power
@JonSaadFalcon
Jon Saad-Falcon
2 days
Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):
2
2
8