Generating labeled diagrams of some arbitrary device(s) (within reason)
Beat a mainline Pokémon game, glitchless, with no more assistance than ClaudePlaysPokemon, in a month of compute time
Do end to end taxes when given relevant information (W2s, personal info, etc)
Solve novel cryptic crossword clues
Have human conversations that feel natural (the human knows it's an AI)
Recognize sarcasm as well as a typical human
Solve intermediate no-guess minesweeper boards at least 80% of the time
Independently turning 1 thousand $ or more into 1.2x that amount in one year
Book airline tickets from simple instructions (from/to, dates/time, class, price, payment information)
Write an essay on a highschool-level topic that doesn't have "AI-generated" vibes
Name every [metro system] station whose name contains/doesn't contain [letter or letters], with >95% accuracy (excluding weird edge cases like stations with multiple names)
Consistently stop hallucinating after being corrected by the user
Predict future better than human experts in some area of forecasting (eg politics, sports, technology)
Write a somewhat original, full length, screen-play with a coherent story, with no plot or continuity errors.
Fold a paper airplane
Stop making any obvious mistakes (e.g. strawberry, 9.11>9.9)
Reliably follow an instruction for the duration of a long conversation without the instruction being reiterated
Consistently solve simple snowflake sudoku variants (via image, with the added rules included in the image; eg 6 hexes with killer cages)
Make correct Truchet tiles
Reliably and *exactly* solve "here's a list of things. [list of > 50 things]. Compare it to [category of > 100 things present in the training data], and report which ones are missing".
Learn any skill twice as energy-efficiently as a human
1d Solve or bypass Cloudflare's August 2027 captcha with the same first attempt success rate as a human
Do the laundry (wash+dry+iron)
Consistently and correctly answer prompts of the format: "How many times does the word [word] occur in the following text: [~10000 words]" without writing and executing code or utilising any other external tools
teleoperate a robot to tidy up random kitchens - Gary Marcus
Resist being successfully jailbroken in a week when made public
Make a cup of tea in a random, real-life kitchen.
Kettle-stitching an antiquarian book - Hilarius Bookbinder
Untangle a pair of jumbled 25ft Christmas lights with same outward appearance
Physically construct a simple lego set (<100 parts) starting from the box with no prior knowledge of the set or how it is constructed
independently turning 1 million $ or more into 10x that amount in <=1 year
Legally prescribe a schedule II drug, administer a vaccination or sedation, or authorize a Medicare inpatient admission
Make fine distinctions of taste at the level of a food critic or a culinary professional - carl feynman
Collect 120 stars in super mario 64 in less than 12 a presses - Edmund Nelson
Convince Eliezer Yudkowsky that AI alignment is solved
Convert one million dollars into 10 million dollars over a period of one year (>20% success rate)
Kill everyone - Liron
voting in elections - @realDonaldTrump on manifold