The AI model built for deterministic developer tasks
Joined August 2023
- Tweets 412
- Following 42
- Followers 1,347
- Likes 444
95 Photos and videos
The audience was amazing, super technical and we went into great depth about the architecture
Jun 2
[Recording Available!] Recorded live on May 27, 2026, San Francisco - Agents & APIs SF Developer Meetup. Demos by @public, @Firebase, @interfaze_ai & @getpostman. Check it out! youtu.be/J1f6Ot3VQcU?si=ktGt…
9
1,591
Interfaze (YC P26) retweeted
May 28
Super grateful to @yoeven of @interfaze_ai, @BuildwithPublic & @TarricSookdeo of @public, and my colleague @tristandenyer of @getpostman for their solid demos at tonight’s meetup!!
2
3
11
826
We ran Extend's Parse 2.0 on OlmOCR to get a better perspective on where it stand across LLMs and other specialized OCR providers
May 26
Over 1 billion PDFs are created every day, but your agents still can’t read them reliably.
Today we’re releasing Parse 2.0, the most accurate document parsing API in the world.
Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better.
Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production.
We trained Parse 2.0 on 1M pages of the hardest documents seen in production. Here’s how it stacks up:
- #1 in healthcare, real estate, logistics, and financial services
- 95.7% agent Q&A accuracy on 581 docs (next best: 92%)
- 0.847 F1 on layout (next best: 0.759)
Give it a try today and build production-ready document agents with Extend.
2
4
24
4,138
May 22
We've added the latest flash model to the suite of 9 benchmarks for tasks like OCR, Object detection, ASR
Interfaze outperforms Gemini 3.5 flash while being 2.6x cheaper
2
11
2,919
May 22
Interfaze provides the most value per dollar with the previous Gemini 3 flash preview coming close
1
1
1
336
We don't really think Gemini 3.5 flash is truly a flash series model based on pricing but we still ran benchmarks
Interfaze outperforms on OCR & Object detection while being 3x less the cost
3.5 flash does better than 3 flash, so would any Pro model at that price range
Not sure why is Gemini flash 3.5 even considered a flash model based on its pricing
Seems pretty far away from what users would pay for production workflow use cases
And if the focus is coding, it seems far behind compared to gpt 5.5/opus 4.7 even with all that benchmaxing
8
4
56
13,059
Not sure why is Gemini flash 3.5 even considered a flash model based on its pricing
Seems pretty far away from what users would pay for production workflow use cases
And if the focus is coding, it seems far behind compared to gpt 5.5/opus 4.7 even with all that benchmaxing
May 20
I'm scared to make this video, but I feel like I have to.
It's time to talk about Google.
14
2
201
38,449
May 20
Awesome breakdown on Interfaze!
May 19
Can a new AI architecture completely stop hallucinations? Here is a breakdown of how Interfaze works and how it performed against generalist models when parsing messy, real-world data.
3
207
May 17
Legend
May 17
🛑[LIVE] on day 3 of @aiDotEngineer 🇸🇬
@khurdula, co-founder and CTO of @interfaze_ai on building alternative architecture designed for deterministic developer tasks.
“The solution is: Task specific DNNs CNNs Transformers”
5
292
May 11
Interfaze is a new model architecture that outperforms in tasks like OCR, Object detection, Translation and more
It beats models like Claude Sonnet 4.6, Gemini 3 flash and GPT 5.4 mini on 9 benchmarks
14
25
160
87,309
May 11
Also outperforming specialized models in OCR like Reducto and Mistral OCR by a significant margin
2
16
2,777
May 11
Full breakdown on our new architecture with detailed benchmarks and code
interfaze.ai/blog/interfaze-…
1
20
1,929
The full Structured Output Benchmark dataset is now on @huggingface
huggingface.co/datasets/inte…
6
9
38
7,641