Penny sample shown looks like failed EXIF orientation registered by the model/harness. The coins are correctly marked, it's rotated 90 degrees.
GPT 5.6 Sol is the best "vision" model OpenAI ever released
11–20 of 194 posts
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#12Anecdotal, opinion: Gpt is really good in vision stuff, or at least their MoE seems to be really cohesive. From my experience Claude models can be really good at language but the moment they need to look at a picture and decide why the design is not good what parts need improvement it degrades a lot. My easiest benchmark is giving them a screenshot of a feature in my app and tell it "identify non-normative UI blocks…
Assessing the subjective quality of a thing is in my experience one of the worst ways to use any LLM.
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#13Earlier quoted context omitted.
How can a vision model have taste?
Replace taste with consistent if that helps you. Can it follow a design system...
As a design system engineer I usually have to fight against the taste of the designers. (And I consider it natural.)
But, if you have a proper well documented design system and you tell the LLM to use the DS and to avoid styling hacks they can generally do it. Even the dumber ones than Sol 5.6.
Of course only if the design is achievable in the design system.
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#14Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#15Earlier quoted context omitted.
Replace taste with consistent if that helps you. Can it follow a design system...
As a design system engineer I usually have to fight against the taste of the designers. (And I consider it natural.) But, if you have a proper well documented design system and you tell the LLM to use the DS and to avoid styling hacks they can generally do it. Even the dumber ones than Sol 5.6. Of course only if the design is achievable in the design system.
This is not my experience at all.
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#16Anecdotal, opinion: Gpt is really good in vision stuff, or at least their MoE seems to be really cohesive. From my experience Claude models can be really good at language but the moment they need to look at a picture and decide why the design is not good what parts need improvement it degrades a lot. My easiest benchmark is giving them a screenshot of a feature in my app and tell it "identify non-normative UI blocks…
What is a "non-normative UI block"?
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#17Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#18Anecdotal, opinion: Gpt is really good in vision stuff, or at least their MoE seems to be really cohesive. From my experience Claude models can be really good at language but the moment they need to look at a picture and decide why the design is not good what parts need improvement it degrades a lot. My easiest benchmark is giving them a screenshot of a feature in my app and tell it "identify non-normative UI blocks…
Assessing the subjective quality of a thing is in my experience one of the worst ways to use any LLM.
anthropic frontend-design skill does a great job with it.
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#19Earlier quoted context omitted.
How can a vision model have taste?
If you're doing any kind of inference that is multi-modal and non-factual, opinions and biases will affect any kind of assessment of a visual that you provide to a model. For example, a UI / UX professional being asked to appraise a website screenshot may determine that the image in question has "desirable" traits which are inherently not deterministically measurable. Such as, if the interface elements have strong in…
> if the interface elements have strong information hierarchy
...but that's an example of a UX/usability matter that can be assessed objectively and non-subjectively.
Re: GPT 5.6 Sol is the best "vision" model OpenAI ever released
#20For the last 2 weeks I've been trying to get Codex to "outpaint" a wonderful image it generated as placeholder art for a level background. After I increased the game's resolution, I asked it to increase the image's size while keeping the same scale and existing content, and gosh, it constantly keeps getting something wrong no matter what I tell it, even on Sol Max with the $100 Pro subscription. An organically-grown…
> it constantly keeps getting something wrong no matter what I tell it
This 100%