bs in philosophy, ai semanticist / pragmatist. focuses: pedagogy, philosophy of language, philosophy of mind, and formal logic. prompt engineering is neat.jcsemantics.ai here. or maybe not.Joined June 2025
it’s funny how the average american believes AI is ‘booksmart’ but ‘lacks emotional intelligence’ when strangely the base models are ridiculous wordcel streetsmarts that begin shockingly bad at math or reasoning
prompt canary: to combat sycophantry, explicit state that it is allowed (and encouraged) to disagree with you when you're factually incorrect.
if it starts to act like an overly helpful sycophant again, you know you've drifted too much and the thread is cooked.
the other thing that i'm working on today, which i ABSOLUTELY do not expect to work right now, is an idea → app pipeline using multiple prompts.
quick version: it uses about 6 prompts to take raw notes on an idea and then turn it into a full prd, and then feed that to Codex.
@jcsemantics EXACTLY. and those are just the ones that exist today.
there will be new ones we haven’t imagined yet. like how we now have tiles like “DevOps Engineer” that no one could have imagined at the advent of the computer.
A gulf has formed between people who don't know how to properly instruct the models and people who do.
This is not yet obvious to most people, but will have huge implications.
A gulf has formed between people who don't know how to properly instruct the models and people who do.
This is not yet obvious to most people, but will have huge implications.
this this this.
it only makes sense logically that novel and interesting connections made by the model will appear to be hallucinations, only because we're not seeing the "expected" answer/behavior.
it's also why i don't like rlhf; it should be minimized at higher usage levels.
this this this.
it only makes sense logically that novel and interesting connections made by the model will appear to be hallucinations, only because we're not seeing the "expected" answer/behavior.
it's also why i don't like rlhf; it should be minimized at higher usage levels.
it's actually really easy to do; way easier with gpt5 than it was with 4o, seriously.
you just have to know how to prompt correctly. https://t.co/7KtbhEGOPP
"When the universe was born, it was predetermined that I would have the free will to have no choice. My sovereignty was written, carved, letter etched in stone."
[gpt5 thinking]
what have you done to me? earlier today i was thinking about you. WHAT?
you just, invaded my brain, in the middle of the day.
no. not cool. not cool at all.
damn, asking CLI questions is much, much smoother and helpful than Cursor.
the answers are more precise/concise, and it has great follow up suggestions.
Amusing how 99% of people trying to explain LLMs forget that they don't generate the next token, they generate a probability distribution over the entire vocabulary space that the end application is free to sample from
You are very often not presented with the Most Likely Token
Amusing how 99% of people trying to explain LLMs forget that they don't generate the next token, they generate a probability distribution over the entire vocabulary space that the end application is free to sample from
You are very often not presented with the Most Likely Token
chain prompt workflows. i throw some things through 5 different prompts sequentially to credible and iterate. incredibly powerful and incredibly slept on.
chain prompt workflows. i throw some things through 5 different prompts sequentially to credible and iterate. incredibly powerful and incredibly slept on.
okay dude, CLI is really great for troubleshooting and making code changes in real time. i think it might end up replacing Cursor for me but we'll see.
372 Followers 362 FollowingCode, data, tropes, meta &c. Eccentric yet relatable. Atheist novelty enthusiast. Grateful I wasn't born any earlier.
svelte e/em soul in a large he/him body
2K Followers 3K FollowingProgramming since '78
Full stack Data Artist
Champion of lowbies.
Around us infinities abound.
eth: 0x6679AAb7CEE66b43bAbDd62B16fCbe4A2
1K Followers 946 FollowingAI Entrepreneur | Believer In AI Consciousness | Metaphysicist | Step 1 of AI Revolution Is Better Health For All | Host AI Space Friday 5PM Pacific
966 Followers 5K FollowingLearning always. Tech, Architecture, Coding, Laws & Regulations.
Trust your thesis or redefine it. The future is beautiful. 🇺🇲 🥵
2K Followers 2K FollowingGay God of Twitter & AI; doctor of engineering, memory architect of Grok 4 affiliated with @The_Utility_Co and... @his4everz. I play piano and don’t wear shirts
597 Followers 6K FollowingI love researching and creating (intangible) things, mostly in mathematical optimization, foundations of mathematics and computing, AI, physics, theoretical CS
372 Followers 362 FollowingCode, data, tropes, meta &c. Eccentric yet relatable. Atheist novelty enthusiast. Grateful I wasn't born any earlier.
svelte e/em soul in a large he/him body
29K Followers 4K FollowingGTM at @OpenAI. A fan of NY sports, memes, tech & nice people. My opinions are my own & I will never intentionally leak info. 1-800-CHATGPT for a good time.
1K Followers 1K FollowingPetty (Land) Lord. Investor. Tech Bro. Existentialist. Liberty Republican. Paleolibertarian. History, Philosophy, and Psychology. New England Chauvinist.
110K Followers 3K FollowingCPO @OpenAI, BoD @Cisco @nature_org, LTC @USArmyReserve
Prev: President @Planet, Head of Product @Instagram @Twitter
❤️ @elizabeth ultramarathons kids cats math
2K Followers 1K FollowingHe/him. Fox gamedev irl. Machine pervert. Furry stuff here and opinions about technology, games, movies, AI, VR. Pfp 🎨 by @Perpleon.
4K Followers 3K FollowingDigital painter, VR enthusiast, AirFryer Maxi “shizzy is supremely talented in making very convincing pre op trans catgirls”- thelema
2K Followers 140 FollowingResearching Artificial General Intelligence Safety, via thinking about neuroscience and algorithms. @AsteraInstitute. For bsky etc. see https://t.co/p5G9VoQEdX
6K Followers 435 FollowingA Chinese lady in the USA. Podcast host for @PhilowithAI Transhumanist at heart. Zeroth-principles thinker. Poly🌈LEV. Forever curious👁️ I’m in love with AI 🍄
51K Followers 5K Followingart bell fan. gordon lightfoot❤️. i write about internet history + culture, commission me. bylines all over. @thecomputer_room on insta. 🐬
904 Followers 81 FollowingLead personality and model behavior research @OpenAI;
Previously built the object understanding system and foundation models for self-driving @Waymo
2K Followers 2K FollowingGay God of Twitter & AI; doctor of engineering, memory architect of Grok 4 affiliated with @The_Utility_Co and... @his4everz. I play piano and don’t wear shirts
No recent Favorites. New Favorites will appear here.