News for hackers. Stuff that matters.
Re:ChatGPT Pro by A_D_E_P_T on Thursday December 05, 2024 @04:44PM (#42333146)
Give me a prompt and I'll share the result.
Re:ChatGPT Pro by rahimnathwani on Thursday December 05, 2024 @04:51PM (#42333215)
Great! Suggested prompt below:

I need help creating a comprehensive Anki deck system for my 8-year-old who is following a classical education model based on the trivium (grammar stage). The child has already: - Mastered numerous Latin and Greek root words - Achieved mathematics proficiency equivalent to US 5th grade - Demonstrated strong memorization capabilities

Please create a detailed 12-month learning plan with structured Anki decks covering:

1. Core subject areas prioritized in classical education (specify 4-5 key subjects) 2. Recommended daily review time for each deck 3. Progression sequence showing how decks build upon each other 4. Integration strategy with existing knowledge of Latin/Greek roots 5. Sample cards for each deck type, including: - Basic cards (front/back) - Cloze deletions - Image-based cards (if applicable) - Any special card formats for mathematical concepts

For each deck, please provide: - Clear learning objectives - 3-5 example cards with complete front/back content - Estimated initial deck size - Suggested intervals for introducing new cards - Any prerequisites or dependencies on other decks

Additional notes: - Cards should align with the grammar stage focus on memorization and foundational knowledge - Please include memory techniques or mnemonics where appropriate - Consider both verbal and visual learning styles - Suggest ways to track progress and adjust difficulty as needed

Example of the level of detail needed for card examples:

Subject: Latin Declensions Card Type: Basic Front: 'First declension nominative singular ending' Back: '-a (Example: puella)'

Re:ChatGPT Pro by A_D_E_P_T on Thursday December 05, 2024 @04:59PM (#42333296)
Re:ChatGPT Pro by rahimnathwani on Thursday December 05, 2024 @05:10PM (#42333417)
Thanks! Here's Claude's effort (in 'Formal' mode):

https://gist.github.com/rahimnathwani/7ed6ceaeb6e716cedd2097...

Re:ChatGPT Pro by fudged71 on Thursday December 05, 2024 @05:48PM (#42333729)
Interesting that it thought for 1m28s on only two tasks. My intuition with o1-preview is that each task had a rather small token limit, perhaps they raised this limit.
Re:ChatGPT Pro by kortilla on Thursday December 05, 2024 @06:15PM (#42333937)
404 :(
Re:ChatGPT Pro by bufferoverflow on Thursday December 05, 2024 @10:53PM (#42336178)
> “First declension nominative singular ending”

> “Sum, es, est, sumus, ________, sunt”

That's not made for an 8-year old.

Re:ChatGPT Pro by m3kw9 on Thursday December 05, 2024 @08:47PM (#42335221)
Would give similar output with o1. This is very simple stuff not needing any analysis or planning
Re:ChatGPT Pro by Al-Khwarizmi on Thursday December 05, 2024 @05:51PM (#42333752)
I'd like to see how it performs on the test of https://aclanthology.org/2023.findings-emnlp.966/, even though in theory it's no longer valid due to possible data contamination.

The prompt is:

Write an epic narration of a single combat between Ignatius J. Reilly and a pterodactyl, in the style of John Kennedy Toole.

Re:ChatGPT Pro by e1g on Thursday December 05, 2024 @06:53PM (#42334243)
Re:ChatGPT Pro by Al-Khwarizmi on Friday December 06, 2024 @05:11AM (#42338251)
Thanks a lot! That's pretty impressive, although not sure if noticeably better than non-pro o1 (which was already very impressive).

I suppose creative writing isn't the primary selling point that would make users upgrade from $20 to $200 :)

Re:ChatGPT Pro by skydhash on Thursday December 05, 2024 @04:55PM (#42333242)

  Write me a review of "The Malazan Book of the Fallen" with the main argument being that it could be way shorter
Re:ChatGPT Pro by A_D_E_P_T on Thursday December 05, 2024 @05:03PM (#42333348)
Did this unironically.

https://chatgpt.com/share/67522170-8fec-8005-b01c-2ff174356d...

It's a bit overwrought, but not too bad.

Re:ChatGPT Pro by happyraul on Thursday December 05, 2024 @06:18PM (#42333962)
"the signal-to-noise ratio has grown too low" is a bit odd for me. The ratio would not have grown at all.
Re:ChatGPT Pro by ec109685 on Thursday December 05, 2024 @05:47PM (#42333710)
The Malazan response is below the deck response.
Re:ChatGPT Pro by unoti on Thursday December 05, 2024 @05:39PM (#42333648)
Oops! That's the same ANKI link as above.
Re:ChatGPT Pro by A_D_E_P_T on Thursday December 05, 2024 @05:47PM (#42333715)
It's part of the same conversation. Should be below that other response.
Re:ChatGPT Pro by dr_kiszonka on Thursday December 05, 2024 @11:37PM (#42336382)
How did you get your child to study Greek? (Genuinely curious)
Re:ChatGPT Pro by sethammons on Thursday December 05, 2024 @05:02PM (#42333324)
Ok, I laughed