Ramesh Pathak

— hand it your website and a budget. it runs your meta ads.
building AI agents, posting the notes
prev naamche (acquired)

[Ramesh Pathak @actuallyramesh]

We need new evals AND more skepticism, of a different kind, for AI-rendered information.

What's a canonical AI image failure you'd bet is still broken?

[Ramesh Pathak @actuallyramesh]

For 3 years, image AI had a set of canonical failures we joked about:

– Analog clocks always at 10:10
– Wine glasses never to the brim
– Counting past 6 objects breaks

In May 2026, both SOTA models — gpt-image-2 and Nano Banana Pro — have quietly solved them.

Not perfectly. But the canonical failure modes are gone.

[Ramesh Pathak @actuallyramesh]

So where's the uncanny valley now?

Not in pixels. Not in counts. Not in clocks.

The new uncanny valley is in reasoning made visible:
– Diagrams that look correct but encode wrong algorithms
– Recipe cards with confidently-wrong nutrition
– Charts with plausible-but-hallucinated data

Pretty + wrong, instead of ugly + obviously fake.