ZeljkoS

To me, the real lead of the article is buried here:

> apparently they tried the model on about 8,000 problems. So, right now it “merely” solves ~5% of the longstanding open mathematical problems that it’s asked about, the problems that whole communities have spent years on, after a single 3-hour attempt on them.

Back-of-the-envelope cost calculation:

3 hours of GPT-Pro compute per attempt / 5% success rate → 60 hours of compute per solved open math problem

At GPT-6 Astra API long-context pricing ($75/M output tokens), assuming 50 reasoning tokens/s, that's roughly $810 per solution:

60 h × 3,600 s × 50 tokens/s × $75 / 1,000,000 = $810

Of course, actual token usage is unknown. But even if off by 10x, $8100 is cheap for solving a longstanding mathematical problem.

"The two leaders score 100% on 2026 even though the contest ran after their training cutoffs, so recency alone does not cap performance."

Great!

If all plan queries are deterministic, the "Save recipe as Python" action saves the entire process as a deterministic script:

https://www.tamedtable.com/#save-py

Honestly, you are probably not the target user, as you seem familiar with data cleanup scripts and AI agents. I think the target users would be:

A) Non-technical people in your org who clean data by hand because they don't know to automate it.

B) Technical people who want to test multiple queries and preview transformations before generating an AI-driven transformation flow (and are OK with it).

But, it writes an execution plan :) Example here:

https://github.com/ZSvedic/TamedTable/blob/main/spec/test-ca...

And if an action can be done deterministically, then JS code will be generated:

https://github.com/ZSvedic/TamedTable/blob/main/spec/test-ca...

If data cleanup needs to be deterministic, why is so much of it done by humans? Two humans also won't normalize the same table in the same way. The main thesis is that AI data cleanup is cheaper and less mistake-prone than the same work done by a bored intern.

"Unlike other sea slugs, which can only shed minor body parts, Elysia marginata and Elysia atroviridis can autotomize their heads completely from the rest of their body. "