@roboflow

Build & use computer vision models fast ✨ Get started: https://xitter.cf/t.co/QvAsWtf7c8 Conference Oct 22 in SF: https://xitter.cf/t.co/YX4via3TiV

roboflow.com
Joined June 2019
  • Tweets2.3K
  • Following1
  • Followers15.5K
414Media
Roboflow retweeted
SkalskiP
@skalskip9215h
GPT-6.1 Terra beats Astra in our vision benchmarks wtf OpenAI? had to double-check the results - text - object detection - counting also ~47% faster and ~92% cheaper ↓ leaderboards and examples
OpenAI
@OpenAIOct 26
GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
62
48
29
865
72,829
Roboflow retweeted
Roboflow
@roboflowAug 19
We are hosting the Visual Intelligence Summit on October 22 in SF. The physical world is AI's biggest opportunity and the best way to advance humanity in our lifetimes. Few people are building for AI beyond the screen. The Summit is for the people who see it differently and want to be at the frontier of bringing AI into the physical world. If you’re building for that future, join us.
7
16
10
63
64,740
Roboflow retweeted
Aurick Anwar
@007AurickOct 15
Ever wanted to know if you're cooked in an IRL game of chess? 💀 So I built Stockfish IRL. A camera watches a real board, tracks every move, and literally yells at you when you blunder. Built with @roboflow 👇
3
1
13
956
Roboflow retweeted
SkalskiP
@skalskip92Oct 14
Gemini 4 Argon vs GPT-6 Astra YouTube stream tomorrow, Oct 15th, 8 AM PT / 11 AM ET / 5 PM CET save the time and see you tomorrow - detection - segmentation - transcription - data extraction - efficiency and cost what else? link: youtube.com/live/bBX_c5AFuMQ
SkalskiP
@skalskip92Oct 13
Astra dethroned Gemini 4 Argon is the best "vision" model #1 for detection: - tight, precise boxes - dense scenes #1 for text extraction: - small text - handwritten text - complex tables - rotated text 4× cheaper than Astra at high
3
3
1
77
5,278
Roboflow retweeted
SkalskiP
@skalskip92Oct 13
Astra dethroned Gemini 4 Argon is the best "vision" model #1 for detection: - tight, precise boxes - dense scenes #1 for text extraction: - small text - handwritten text - complex tables - rotated text 4× cheaper than Astra at high
Google Gemini
@GeminiAppOct 13
The moment you've been waiting 4… Our new frontier model, Gemini 4 Argon, is rolling out now in the Gemini app to bring your most complex ideas into reality. See how Gemini 4 Argon and our latest updates across the Gemini app help you get the most out of every prompt. 🧵

36
80
18
1,184
129,016
Roboflow retweeted
SkalskiP
@skalskip92Oct 13
Muse Wonder is pretty good vision model suuuuuuuper expensive vs Muse Spark 1.3 - better text extraction - better object detection - 2x faster - 4x more expensive (almost Astra price) ↓ benchmarks and examples
Mark Zuckerberg
@finkdOct 12
Introducing Muse Wonder, our new family of frontier models with state of the art performance for personal and professional agentic work.
9
5
3
62
6,711
Roboflow retweeted
SkalskiP
@skalskip92Oct 9
finally releasing our new OCR benchmark tons of hard examples like this mechanical dial meter - single value extraction - JSON data extraction - document transcription - text localization and recognition - 48 models evaluated ↓ examples and leaderboards
30
42
2
461
26,826
Roboflow retweeted
Alex Bodner
@AlexBodner_Oct 9
My favourite thing about @roboflow Trackers is how easy we made it to swap things and create the best tracker for your case. Swap the tracker, the IoU variant, camera motion compensation, dynamic frame rate or masks, one line change, and see what works best! Any detector works.
12
12
1
133
5,660
Roboflow retweeted
SkalskiP
@skalskip92Oct 8
Haiku 5.5 first look I tested new model from Athropic on object detection and our new text benchmark Haiku 5.5 is better and cheaper than GPT-6 Luna leaderboards and examples ↓ playground.roboflow.com/eval…
Anthropic
@AnthropicAIOct 7
Claude Haiku 5.5, our latest model:
6
12
3
133
9,434
Roboflow retweeted
Erik Kokalj
@erik_kokaljOct 7
openai just released Decisions API, Jev-like "system 1" multi-modal model based on GPT6 Luna! Each egg gets cropped and sent to OpenAI (~270ms latency) and returns P(clean, dirty, cracked). One image crop consumes ~280 input tokens (~$0.03/1K imgs). @roboflow RF-DETR for detecting eggs
210
480
196
7,597
1,869,263
Roboflow retweeted
SkalskiP
@skalskip92Oct 1
I spend a lot of time finding out what VLMs still can't do pretty excited to help change that we launched Roboflow Labs at @roboflow training data, evals and environments for real-world tasks. vision, multimodal reasoning, robotics and coding. link: blog.roboflow.com/roboflow-l…
21
36
3
358
28,940
I just labelled over 1000 segmentation masks for utility poles in under 90 s 🤯 -GPT Astra for box detections -SAM3 for masks on those boxes How long would it take a human to do the same??
20
44
7
697
43,056
Jev-Omni for Quality Inspection, looking at lemons on a roller line, running fully local on MacBook 🍋 - Each lemon gets checked 3 times while it rolls - OK only after 3 clean passes (to cover different sides of the lemon), any defect flags it - Jev-Omni as classifier, @roboflow's RF-DETR (instace seg) as detector, trackers lib for tracking
22
115
28
1,016
296,746
Roboflow retweeted
SkalskiP
@skalskip92Sep 24
Opus 5.5 is the best "vision" model Anthropic ever made better than Fable 5, better than GPT-6 Sol, worse than GPT-6 Astra vs Fable 5.1 (high): - estimated cost: ↓ 60% - detection: ↑ 11.84 pp - reasoning: ↑ 12.80 pp vs GPT-6 Sol (high): - extraction: ↑ 11.00 pp - reasoning: ↑ 7.95 pp ↓ 16 more examples
SkalskiP
@skalskip92Sep 22
fuck me. every lab is working on vision. I have preliminary Opus 5.5 results. by far the best vision model from Anthropic. more soon.
22
27
5
382
38,284
Roboflow retweeted
SkalskiP
@skalskip92Sep 23
going live tomorrow to test GPT-6 Sol and Luna, Opus 5.5, MiMo-V2.6 Pro & Flash and Grok 4.7 Sep 24th, 17:00 CEST / 11:00 EDT / 08:00 PDT link: youtube.com/live/E57bsVJtHT8
1
1
22
1,581
Roboflow retweeted
Brad Dwyer
@braddwyerSep 23
Ok this is pretty insane. Astra side-loaded a custom app for my DJI RC2 controller that takes a live video stream from my Mini 5 Pro drone, streams it to a @roboflow Workflow running RF-DETR via our Serverless Video API, & overlays the predictions back on the controller’s screen.
41
53
11
773
60,991
Roboflow retweeted
SkalskiP
@skalskip92Sep 22
Opus 5.5, GPT-6 Sol, and GPT-6 Luna numbers are on the Playground leaderboard crazy how fast Google lost the computer vision lead object detection used to be their stronghold, now 3 labs and 4 models sit ahead of them link: playground.roboflow.com/eval…
10
15
3
168
11,181
Announcing Joseph Nelson, CEO & Co-Founder of Roboflow as our Keynote Speaker for Iowa Startup Week on Wednesday, September 30. Roboflow is the leading platform for building, deploying, and scaling vision AI applications from data to production. Tickets:buff.ly/Tj3vu9P
1
5
251
Roboflow retweeted
SkalskiP
@skalskip92Aug 13
here are 10 strongest VLMs in my vision benchmark, sorted by cost Gemini 3.7 Flash is insane - 2nd in object detection (behind Qwen3.8-Max) - 2nd in text extraction (behind Gemini 3.5 Flash) - 2nd in image reasoning (behind Gemini 3.5 Flash) - over 3x cheaper than Gemini 3.5 Flash - over 2x cheaper than Qwen3.8-Max benchmark: playground.roboflow.com/eval…
16
28
4
367
25,148
Roboflow retweeted
SkalskiP
@skalskip92Aug 4
wanna test Qwen3.8-Max object detection on your images for free? we spent the past two days adding support for the latest Qwen model in Roboflow Playground upload the image, tell us what you want to detect link: playground.roboflow.com/shar…
SkalskiP
@skalskip92Aug 3
Qwen3.8-Max is the best object detection VLM - satellite images - infrared images - documents - techical drawings - hand-sketched diagrams - crowded scenes - small objects ↓ check out some of those insane examples
6
21
207
17,575
Load more