Pinned Tweet
For the past few months, Piinc has been pushing generative media models to their limits with image and video evals based in real creative workflows. We've gotten close and personal with these models and their unique strengths. We document our high-level learnings on the Piinc blog: perceptualinsights.ai/the-bl… #genmedia #multimodal #genAI #evals
What happens when an AI agent gets to an answer faster than the human can even start to unpack the problem? This question has been bothering me, particularly because of the human psychology involved. Written as a bite here: substack.com/profile/4191813… When someone (human or machine) regularly thinks and responds faster than you, you start to question their assumptions less frequently, you let them take more decisions - unchecked. I wonder if the solution is not slower AI development, but slower agent responses, deliberate pauses in execution to let the humans catch up just enough with the thought process, to make sure it is headed in the right direction...
🤖 Made with AI
2
323
There is no such thing as “the best” generative model for editing. Image editing covers a broad spectrum of tasks with different use cases and user expectations. An image editing task can entail removing a small defect from an image or completely re-imagining a scene. What users expect for these tasks are entirely different outcomes, yet the common tendency in model benchmarking is to collapse all cases into a single ranked set of models. Our evals show that a model that tops the charts for one workflow may not be the best choice for a different workflow. And when measured with professional workflows in minds, the models on the market today produce less than 30% usable outputs. perceptualinsights.ai/no-bes…
4
185
I describe my career journey from my undergrad days in AI, grad school at MIT, industry research and GenAI evals jobs, and recently founding my own company substack.com/home/post/p-190… to give others the confidence to make their own career pivots towards greater personal meaning
6
480
substack.com/@perceptualinsi… for weekly "perceptual bites", or how knowledge from perceptual & cognitive science can be translated into product differentiators, or “what you don’t know you don’t know” about human perception :)
1
157
15 "Mundane" Ways I've Used #ChatGPT in My Family Life in the Last 6 Months open.substack.com/pub/zoyath…
1
4
282
Funny how easy it is to tell that ChatGPT has been used for an email or resume by all the semi-regular bold formatting distributed throughout the text, where what is emphasized is not always semantically consistent. To the human authors: do consider if the bold is always needed.
126
Love this demonstration of how differently we experience and explore our world from even the first days of life.
4
589
Creativity is still in the creator's hands. I had a vision in my head that I could barely translate into words. I used different models to see which would best understand me. None fully did, but they took me down new alleys, like philosophical chats over wine with new friends...
3
223
I was thinking about our place in the era of AI #superintelligence. I wrote down my partial, fleeting yet connected thoughts. And then I decided to leave them as is, a poem of sorts, in free verse. Unpolished and raw like the thoughts themselves: medium.com/@zoya.gavr/we-are…
1
209
I have quite a few friends who are new or expecting parents right now, so I wrote them a letter, reflecting on what I thought it would be most helpful for them to know. Decided to share it more broadly in case it helps others too: zoyathinks.substack.com/p/a-… #parenting
1
178
"When Evals are Not Data Annotation", another in my series of blog posts about #GenAI #evals: medium.com/p/when-evals-are-…
1
158
A reflection of today's reality: seeing utter disappointment in my kids' eyes after trying to talk to Furby (the artificial "intelligent" toy from my childhood) and realizing that unlike ChatGPT, Alexa, or Ok Google, it can not answer their questions. That it randomly farts was seen as a redeeming quality.
2
237
In my previous post I talked about the properties of an #evals job (i.e., the job of building human-powered evaluations for GenAI tools) that requires some of the same skills HCI & Psych researchers already have. I got some questions after that post about how to better align oneself with a career in evals, given a background in these fields. I thought it would help to dig deeper into how evals has evolved into a job, why it’s different than the jobs that came before it, and what it borrows methodology from, as a way of describing the influences that feed into it, and as a result, the diverse tools it helps to have to be good at it. medium.com/@zoya.gavr/evals-…
1
157
For my HCI and psych friends who are thinking about career paths in industry, there are some pretty cool opportunities in evals for GenAI right now: medium.com/@zoya.gavr/why-ev…
The irony! Was reading "The Design of Everyday Things" by @NormanDon on the plane, only to get off and end up helping a visually impaired young woman navigate the ladies room at SFO. Near-missing multiple walls (we had to turn 5 corners!), garbage bins, stools (?!), and people walking in multiple directions at once, made me see the #accessibility challenges through her eyes. "I hate hate HATE public bathrooms" she mumbled under her breath as we meandered through. And this was after standing in a long line because no one in the line realized there were a bunch of empty stalls around a corner 🙈🤦♀️
1
196











