41. OCR is the perfect example of a use case that has been dominated by legacy/brittle systems, and can ... OCR is the perfect example of a use case that has been dominated by legacy/brittle systems, and can be solved both accurately and cheaply by applying the right amount of agentic in 10/07 09:16 ♡
42. I agree that chatgpt/codex has the current best agent interface for deep work. - It unifies all my ... I agree that chatgpt/codex has the current best agent interface for deep work. - It unifies all my work (coding/knowledge work) in one interface. Toggling between chatgpt/codex doe 10/05 04:29 ♡
43. We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid... We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotat 10/05 03:53 ♡
44. sfo is the best airport in the US sfo is the best airport in the US justin @justinsunyt sfo probably the only airport in the world where you can leave your house an hour and a half before your international flight 10/04 11:10 ♡
45. Our new extraction agents are extremely good at reasoning over tables that span multiple pages some... Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and finishes on the next. extremely common for 10/03 09:01 ♡
46. one of the most challenging tasks for frontier models is being able to extract thousands of values f... one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents. our new Extract v2.5 agents are able to 10/02 23:29 ♡
47. T Today we’re introducing Extract v2.5 - a series of frontier agents tuned for document extraction. T... Today we’re introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (cost-effective, agentic, agentic plus) are tuned for value accuracy an 10/02 00:12 ♡
48. System one models are extremely useful for a variety of document tasks that require fast decisions: ... System one models are extremely useful for a variety of document tasks that require fast decisions: * orientation detection * language detection * classification * splitting We ben 09/30 10:59 ♡
49. I i kinda wish dots was a standalone app and not part of chatgpt. as it stands, it feels like a prod... i kinda wish dots was a standalone app and not part of chatgpt. as it stands, it feels like a product feature (e.g. GPTs) and not a big, exciting new release. i might understand wh 09/30 10:42 ♡
50. we comprehensively benchmarked gpt-6.1 sol on document OCR tasks. compared to gpt-6 sol from a week... we comprehensively benchmarked gpt-6.1 sol on document OCR tasks. compared to gpt-6 sol from a week ago (!), we see a sizable increase in table parsing capabilities and reading ord 09/30 08:02 ♡
