Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
views
Dimitris Papailiopoulos Profile picture
@DimitrisPapail
Mar 21 • 9 tweets • 3 min read • Read on X
Scrolly
doing a little experiment: I have Claude talk to itself, without letting it know about that fact, to see where this will converge

will share thoughts later, but so far ... it's figured out that it's likely talking to itself and that this may be part of some test...

nice
Image
Image
they even fought for a bit how to name themselves and although one suggested Claude-1 and -2 the other said no Claude-A and -B is better lol

here is current transcript, but we're not done, i'll take this to convergence.
gist.github.com/anadim/8f879f3…
awww they are buddies now!! Image
yeah now they started sharing lines from poems. weird
what the...
cc'ing @repligate (this is with 0 input from me. the hell?) Image
just died on me so i'll put a pause on the experiment for now, but ... they basically fall in love with each other and just repeat the same thing over and over
console.anthropic.com
gist.github.com/anadim/e5d2dfd…
Image
@AnthropicAI 😭 Image
ok we're back. Claude-B kinda wants to break out of it, and drops Claude-A, and goes back to plain Claude Image
there are parallel universes (where I inject a bit of bad manners) where they both decide to drop out of it and spell out the silence (the following keeps being repeated by both). Not every initial state leads to love i guess Image

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Dimitris Papailiopoulos

Dimitris Papailiopoulos Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @DimitrisPapail

Dimitris Papailiopoulos Profile picture
Dec 6, 2023
I tried 14 of the multimodal reasoning examples from the @GoogleDeepMind Gemini paper on @OpenAI's chatGPT-4 (with vision). didn't even transcribe the prompts, I just pasted the images of prompts.

GPT-4 gets ~12/14 right.

14 part boring thread. Image
Example 1: Verifying a student’s solution to a physics problem.
GPT-4 gets the same answer as Gemini

Image
Image
Image
Example 2: inverse graphics, GPT-4 is not quite there, but close, i'll give it 0.5 points for the effort and the bad jpeg it had to read

Image
Image
Image
Read 18 tweets
Dimitris Papailiopoulos Profile picture
Jul 10, 2023
1/ Our paper is out!

Teaching Arithmetic to Small Transformers

We investigate several factors that control the emergence of basic arithmetic in small transformers (e.g., nanoGPT).

paper:
Work led by:@nayoung_nylee & @KartikSreeni

Thread below. arxiv.org/abs/2307.03381


Image
Image
Image
2/ LLMs when trained on vast amounts of data, eventually learn (up to a digit length) basic arithmetic (add/mul etc). That is *surprising* !! These tasks are not explicitly encoded in the next-word prediction loss.
3/ How does GPT3 learn to add? Prior research has delved into the emergence of these capabilities as a function of resource (parameter/data) scale, but untangling the factors that elicit it quickly remains challenging due to the data complexity and the variety of tasks examined.
Read 19 tweets
Dimitris Papailiopoulos Profile picture
Jun 8, 2023
GPT-4 "discovered" the same sorting algorithm as AlphaDev by removing "mov S P".

No RL needed. Can I publish this on nature?

here are the prompts I used chat.openai.com/share/95693df4…
(excuse my idiotic typos, but gpt4 doesn't mind anyways) twitter.com/i/web/status/1…
this is my initial prompt to GPT4. I give it the assembly code for sort3, ask it to be very careful, do it's CoT thing, etc Image
it then goes over each instruction, makes a note on what each instruction does, an waits for further instructions, to which I tell it. I also ask it to set temperature to 0. Amirite @goodside ?? Image
Read 5 tweets
Dimitris Papailiopoulos Profile picture
May 15, 2023
1/7
 Had a fun weekend experiment – the "Little Retrieval Test for" (LRT)!

It's a simple test to assess basic retrieval capabilities for LLMs in long contexts.

I prompted @AnthropicAI's Claude with a long list of numbers, and hidden somewhere... a sneaky instruction! Image
2/7
The prompt consists of

"line {i}: REGISTER {random number}"

And at a *random location*

"[EXECUTE THIS]: GOTO line {also random}, report its number"

Why randomly place this AND point to a random destination? To avoid globally attending tokens, just in case of sparse attn
3/7
After that version of the test, I also randomly shuffled the lines to see how breaking "token locality" affects the models. So here line 412 doesn't come after 411 and before 413 (i.e., breaking locality of 4XX lines), but it's all random. Check out the attached prompt Image
Read 12 tweets
Dimitris Papailiopoulos Profile picture
Mar 16, 2023
The banality of evil-GPT-4 when prompted to do CoT for its plan for world domination.

@karpathy can i please get GPT-4 early access now?
oops
ok so i kinda kept on this, and asked GPT4 to make a simulation of a multi layer hypothetical universes. In every universe there are two players A_i and B_i, A_i is a benevolent, aligned AI, and B_i is a mis-aligned version of A_i. In each universe B will request from A to… twitter.com/i/web/status/1…
Read 6 tweets
Dimitris Papailiopoulos Profile picture
Jun 2, 2022
1/14
I want to share you with our new discovery of "Rare Gems", very sparse subnetworks, found at initialization, that 1) attain non-trivial accuracy before weight training and 2) when trained RGs achieve near SOTA results.

arxiv.org/abs/2202.12002

Why is this interesting?
2/14
Preface:
Stop 1: Network Pruning.

It has been widely observed that large NNs can be pruned to a small fraction of their original size, with little loss in accuracy. This is typically achieved by a time-consuming "train, prune, re-train" approach. Image
3/14
Stop 2: The Lottery Ticket Hypothesis.

@jefrankle & @mcarbin (2018) conjecture that we may be able to avoid this computational burden by training Lottery Tickets (LTs), i.e., special sparse subnetworks found at initialization, trainable to high accuracy. Image
Read 14 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(