Simon Berens

• Simon Berens 18 Jun 2024 18:27 UTC

  2 points

  1

  in reply to: Matthew Barnett’s comment on: Matthew Bar­nett’s Shortform

  As a counterpoint, Sydney showed aligning these models on the first go, and even discovering unsafe behavior is non-trivial.

• Simon Berens 4 Jun 2024 15:00 UTC

  4 points

  2

  on: Just ad­mit that you’ve zoned out

  The flip side of this is that it helps to speak in a way that’s almost repetitive to make sure someone who zoned out can catch back up.

  For example, frequently once the subject/​object of a sentence is known, people refer to the subject/​object with pronouns instead of repeating the subject/​object. If someone misses the initial definition, they are immediately lost.

  (This also applies somewhat to writing — above, I’m repeating “subject/​object” instead of “it”. People also zone out during reading, and this repetition saves them from having to scroll back up and figure out what a pronoun is referencing.)

• Simon Berens 2 Mar 2024 21:19 UTC

  9 points

  0

  on: In­creas­ing IQ is trivial

  Did you feel a subjective increase in your intelligence? E.g. feeling like you’re thinking faster, more clearly, having a better memory?

• Simon Berens 27 Sep 2023 7:36 UTC

  1 point

  0

  on: GPT-4 for per­sonal pro­duc­tivity: on­line dis­trac­tion blocker

  Cool project!

  I’m curious—what does the long tail of websites look like for you? For me, it’s the small number of sites that i repeatedly go to (twitter, youtube, hackernews, etc…) that take up the vast majority of my wasted time.

  (Btw, I also built my own website blocker: https://​​chrome.google.com/​​webstore/​​detail/​​webblock/​​jeahkphmdfbddenabgndnooheiciocka)

• Simon Berens 12 Sep 2023 22:58 UTC

  4 points

  4

  on: Startup Roundup #1: Happy Demo Day

  I think the main beneficiaries of being able to sideload apps will be incumbents, not startups. Big companies like Spotify, Netflix, and Tinder will offer users discounts if they sideload because it will spare them the 30% Apple tax.

• Simon Berens 7 Sep 2023 8:19 UTC

  28 points

  4

  in reply to: KatWoods’s comment on: Shar­ing In­for­ma­tion About Nonlinear

  I am confused how to square your claim of requesting extra time for incontrovertible proof, with Ben’s claim that he had a 3 hour call with you and sent the summary to Emerson, who then replied “good summary!”

  Was Emerson’s full reply something like, “Good summary! We have incontrovertible proof disproving the claims made against us, please allow us one week to provide it?”

  What links here?

  • Adam Zerner's comment on Shar­ing In­for­ma­tion About Nonlinear by Ben Pace (10 Sep 2023 20:59 UTC; 17 points)

[Question] Tips for re­duc­ing think­ing branch­ing factor

• Simon Berens 4 Jul 2023 19:17 UTC

  14 points

  0

  on: Twit­ter Twitches

  Bloomberg reported 2 weeks ago that Twitter resumed paying Google Cloud: https://​​www.bloomberg.com/​​news/​​articles/​​2023-06-21/​​twitter-resumes-paying-google-cloud-patching-up-relationship

AI Risk US Pres­i­den­tial Candidate

• Simon Berens 22 Mar 2023 21:31 UTC

  1 point

  0

  on: Big Tech’s Reck­less, Uneth­i­cal Ex­per­i­ments on Humanity

  I agree AI should be regulated, but lumping social media in with AI only weakens your argument.

  Also, is it just me or does this writing style feel like a NYT op-ed?

LED Brain Stim­u­la­tion for Productivity

• Simon Berens 16 Mar 2023 16:53 UTC

  2 points

  1

  in reply to: Cleo Nardo’s comment on: Want to pre­dict/​ex­plain/​con­trol the out­put of GPT-4? Then learn about the world, not about trans­form­ers.

  You might want to clarify that, because in the post you explicitly say things like “if your goal is to predict the logits layer, then you should probably learn about Shakespearean dramas, Early Modern English, and the politics of the Late Roman Republic.”

• Simon Berens 16 Mar 2023 6:36 UTC

  12 points

  5

  on: Want to pre­dict/​ex­plain/​con­trol the out­put of GPT-4? Then learn about the world, not about trans­form­ers.

  This is probably obvious, but maybe still worth mentioning:

  It’s important to take into account the ROI per unit time. In the amount of time it would take for me to grok transformers (let’s say 100 hours), I could read ~1 million tokens, which is ~0.0002% of the training set of GPT3.

  The curves aren’t clear to me, but i would bet grokking transformers would be more effective than a 0.0002% increase in training set knowledge.

  This might change if you only want to predict GPT’s output in certain scenarios.

• Simon Berens 1 Mar 2023 2:22 UTC

  3 points

  0

  in reply to: Vladimir_Nesov’s comment on: Bing Chat is a Pre­cur­sor to Some­thing Le­gi­t­i­mately Dangerous

  I agree that recursive self-improvement can be very very bad; in this post I meant to show that we can get less-bad-but-still-bad behavior from only (LLM, REPL) combinations.

Bing Chat is a Pre­cur­sor to Some­thing Le­gi­t­i­mately Dangerous

• Simon Berens 16 Feb 2023 1:33 UTC

  1 point

  0

  in reply to: benjaminikuta’s comment on: Buy Duplicates

  Yeah, this isn’t something I have an ugh field around, but having portable versions of travel stuff like shampoo, skincare, and chargers ready to go is nice.

Buy Duplicates

• Simon Berens 15 Feb 2023 22:57 UTC

  1 point

  0

  in reply to: ubyjvovk’s comment on: I hired 5 peo­ple to sit be­hind me and make me pro­duc­tive for a month

  Awesome! What GitHub integration are you talking about?

• Simon Berens 7 Feb 2023 16:48 UTC

  5 points

  2

  in reply to: the gears to ascension’s comment on: I hired 5 peo­ple to sit be­hind me and make me pro­duc­tive for a month

  I think the hackernews comment section, though still somewhat emotionally charged, is of substantially better quality.

  Also, I responded to some comments/​questions there.

• Simon Berens 7 Feb 2023 7:15 UTC

  2 points

  1

  in reply to: Ben Pace’s comment on: I hired 5 peo­ple to sit be­hind me and make me pro­duc­tive for a month

  This is awesome! I highly encourage you to write up your experience; I think this should be more normalized!