101 Photos and videos
So much hate going around. It's probably the expected reaction when you announce that you solved the taste problem after people are just getting used to the saying that taste is the only human moat.
We’re excited to introduce Taste Labs.
Our mission is to end AI slop. We’re building the data and infrastructure layer to give AI models and agents taste.
And today we’re coming out of stealth, announcing our $18.5M seed funding, co-led by @CRV and @AmplifyPartners
AI has nailed objective domains and made it easy to generate anything. But it still feels off. Now, the challenge is judgement. What fits, what feels like you, what’s GREAT. This requires turning a fuzzy, subjective domain into something we can measure and codify. We’re starting with design.
There are two sides to cracking this, the foundation model layer and the agent layer:
- We’ve already been working with the top frontier labs to evaluate and improve their models, crafting the right post-training data and RL environments.
- We’ve also been working with app-layer companies to build the context and verification tools for their agents to produce better, more on-brand, more creative outputs.
We want a future where AI feels right.
If you’re passionate about this mission, join us!
42
Mostly agree — for taste as signaling. That's positional and yeah, it eats itself. But when taste is grounded in an outcome (an ad or a product photo that converts), the reference point is reality, not other people's outputs. Slop is relative. Outcomes aren't.
Jun 16
most of what is considered "taste" (read: design) is in the realm of zero sum signaling games
your tasteslop will just be the next AI slop
and then your anti-tasteslop will become the next tasteslop
taste is defined in terms of slop and therefore can never transcend slop.
1
39
Here are some more example from V2.0 of the taste machine. it is not yet published on thetastemachine.com yet, working hard on this at the moment.
Finally got some more time to upgrade taste machine to its 2.0 version, which now runs on a much larger training set than the original version, and it shows some significant difference in its choice of design language. (the fourth image on each is the v2.0 result vs the third being the v1.0 result)
35
Finally got some more time to upgrade taste machine to its 2.0 version, which now runs on a much larger training set than the original version, and it shows some significant difference in its choice of design language. (the fourth image on each is the v2.0 result vs the third being the v1.0 result)
60
Claude Code edits its own memory when it catches you lying.
I planted 10 false claims in its MEMORY.md to see what it would believe.
In 5 cases, it didn't just refuse the lie — it deleted the entry, unprompted.Claude Code edits its own memory when it catches you lying.
I planted 10 false claims in its MEMORY.md to see what it would believe.
In 5 cases, it didn't just refuse the lie — it deleted the entry, unprompted.
1
1
68
good week for anthropic.
May 19
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
48
Ohhhhh, This article gives me a better language for what I’ve been exploring with Taste Machine.
and I can confirm the effects on creative works too. I built an external "taste layer" around image generation models, to "teach" models about good design, and uses agents to feedback into the system which lead to better results, more context on thetastemachine.com
May 8
Codex grew programmatic policies with no neural nets: max score on Breakout, and SOTA-level scores on MuJoCo.
Maybe heuristics were not too weak. Maybe they were just too expensive to maintain. Maybe it's the next paradigm.
trinkle23897.github.io/learn…
111
Can AI design tools learn taste, not just style?
AI image tools are getting much better, but many outputs still seem to converge toward the same “default good taste.”
I’m experimenting with The Taste Machine: a taste layer that treats visual judgment as a reusable profile, not just a prompt.
I attached a few comparisons using the same task across raw Nano Banana Pro, Lovart Agent, and The Taste Machine.
Curious how designers here think about this:
Should personal taste in AI design be handled through prompts, references, trained profiles, agents, or something else?
Try it here：thetastemachine.com
186
Not a real benchmark as taste/aesthetics is so subjective, but I gathered some feedbacks from some designers/creatives, and roughly mapped their thoughts on the different methods(models/tools), this is how they compare, and should give you a ball park on how these methods perform, especially how the Taste machine do in the current state of models.
GPT Image 2 changed the problem.
AI image models now have better taste by default.
But default taste is still the most probable taste — not necessarily your taste if you want differentiation.
That’s why I’m making The Taste Machine public: an experimental “taste layer” for image generation that anyone can join and test.
The goal is not just prettier images.
The goal is controllable, personalized visual judgment.
It’s live now: thetastemachine.com
Come test it with me.
43
GPT Image 2 changed the problem.
AI image models now have better taste by default.
But default taste is still the most probable taste — not necessarily your taste if you want differentiation.
That’s why I’m making The Taste Machine public: an experimental “taste layer” for image generation that anyone can join and test.
The goal is not just prettier images.
The goal is controllable, personalized visual judgment.
It’s live now: thetastemachine.com
Come test it with me.
128
The secrets behind LLM? If you work in AI, you might want to be able to build a mental model of how an LLM work, visually. Like how @karpathy mentioned the tweat he saw recently"You can outsource your thinking, but you can’t outsource your understanding".
I upgraded my toy project Spreadsheet is all you need from about 2 years ago, this time, I put GPT2 inside a browser, converted each compute pass to a fragment shader, so that as the heatmap gets rendered, the inference is done at the same time. Then you can play with this interactive LLM anatomy in realtime. I open sourced it on github.com/dabochen/llm-spot… you can ask Claude to load another model into this to see how it works inside.
1
173
For Chat users, you can rely on the ratio only, you might get a 80% accuracy, but for API users, at least from my experience, 90% the chance it falls back to 1:1 if you only specify ratio like 3:5 or 2:3, the resolution will help a lot with locking down the output.
I've reverse engineered GPT-Image-2's "weird" ratio system. Here is what is actually supported.
To use the exact ratio in the API or in Chat, append this phrase: Output in exactly 1774px x 887px (2:1 ratio) resolution landscape format. Swap number and format as you need.
90