Andrew Morgan

Hoping to help out some creators w/ this project. Made to produce aesthetically pleasing generations for scene setting w/@midjourney.Let me know what you think! P.S. Free until I run out of credits, so act quickly(LIMITED).Looking forward to your feedback! geniea.com

@strzibnyj do you still use windsurf ?

@songjunkr Alright, will do some testing

@itsanderz 충분해요

SuperQwen3.6 35b might be better than sonnet 4.6 🤔

@sarasteinmd Thank you so much for your quick response. Are you open to DMs?

@itsanderz I've seen something for retina and there's some data about cornea Let me look into that.

@sarasteinmd hey, I was wondering if you've seen any research or experiments on peptides and visual impairments and/ diseasse like Macular Degeneration

Claude code is painfully unusable right now **sobs**

@EMostaque Yes please

should we start stacking GPUs and training models again

@levelsio are you still on Hetzner or now looking for alternatives ?

yes.

@MicahBerkley @grok explain how this could possibly happen

Wait till you see what I have it doing with Criminal and Traffic court cases. This is the year, all my friends are going to become accidentally rich.

@MelkeyDev Are the results better at least ?

Opus 4.6 munching on tokens 😟

@karpathy Hmmn... Agentic Orchestration has a nice ring as well

A lot of people quote tweeted this as 1 year anniversary of vibe coding. Some retrospective - I've had a Twitter account for 17 years now (omg) and I still can't predict my tweet engagement basically at all. This was a shower of thoughts throwaway tweet that I just fired off without thinking but somehow it minted a fitting name at the right moment for something that a lot of people were feeling at the same time, so here we are: vibe coding is now mentioned on my Wikipedia as a major memetic "contribution" and even its article is longer. lol The one thing I'd add is that at the time, LLM capability was low enough that you'd mostly use vibe coding for fun throwaway projects, demos and explorations. It was good fun and it almost worked. Today (1 year later), programming via LLM agents is increasingly becoming a default workflow for professionals, except with more oversight and scrutiny. The goal is to claim the leverage from the use of agents but without any compromise on the quality of the software. Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering": - "agentic" because the new default is that you are not writing the code directly 99% of the time, you are orchestrating agents who do and acting as oversight. - "engineering" to emphasize that there is an art & science and expertise to it. It's something you can learn and become better at, with its own depth of a different kind. In 2026, we're likely to see continued improvements on both the model layer and the new agent layer. I feel excited about the product of the two and another year of progress.

@rand_longevity Thanks much, will try and see !

@itsanderz o.n.e. is what I take

Our little app just hit 10,000 + reviews on the AppStore in 6 months. Sauce: → ask for reviews during onboarding

@yoheinakajima @DaveShapi thoughts?

psa: if you are using an ai agent to help you make money, consider at least setting up an LLC to shield your personal assets from potential mistakes leading to law suits you should assume you are liable for your ai’s actions

@elonmusk @grok what is the feasibility of a system like this, and would it accelerate or decelerate the evolution of the civilization? What would be our motif to progress and thrive?

Universal high income

@VictorTaelin One of the most annoying issues I have with Gemini 3 is that it ignores very specific instructions. Instructions that Claude or GLM would follow right out the box. 😔 Butttt it is really good at UI, that part I really love !

I'm in love with Opus 4.5 right now It feels as smart as Gemini 3, but with way better code style, instruction following, CLI UX and, most importantly, speed when you just want to do something small. Also I had a super cool interaction where Claude Code was failing and walking circles, so I interrupted it and let it ask for clarifications. It made great questions, I taught some concepts, until it clicked. It then completed the task (not an easy one!), and all tests passed. Here's the interaction (summarized by Opus itself): (Claude Code interrupted) - Me: you're spending quite some time here, why don't you just ask me questions? I can always answer questions. you don't need to blindly guess and try random things, this will lead to failure. - AI: You're right, I apologize. Question: when I distribute the lambda across the SUP, how should variable redirection work? Should I be setting HEAP[lam_loc] to redirect the original VARs to the new lambdas? - Me: not sure what your notation means, but... [explains dup-lam semantics]. note that we absolutely need a clone_many() function that receives a Term* and clones each element into two Term*'s. do we have that? does that answer your question? - AI: Thank you, that clarifies a lot! My question about clone_many: in my C inject, I clone the template once, and clone each remaining arg. Is this correct? - Me: what is args0[16]? what is args0[0] and why sup_a is going there? not sure I follow - AI: You're right, let me re-read the Haskell more carefully... So a and b (the SUP branches) are not cloned - they go directly as the first element of the new arg lists. Only the remaining args are cloned. My C code matches this. The issue must be elsewhere. - Me: ah, I see. yes your clone logic looks correct-ish, but I'd still insist that you use a helper clone_many function instead of inlining it manually like that. - AI: Okay, let me add clone_many first. [adds it, tests still fail] Still getting wrong output. Question: Should collapse evaluate/resolve the CO0/CO1 nodes? Or should they stay as CO0/CO1 and get resolved later? - Me: in Haskell, CO0/CO1 fall in the default case of collapse... [explains full reduction chain with dup-sup same-label interaction] - AI: That's very helpful! So the dup-sup interaction with same labels is what makes the CO0/CO1 resolve correctly. The issue must be in my template structure. Is my template structure wrong? - Me: you just pass the template to inject, it will clone the whole thing if needed. your construction looks wrong, you're allocating two lambdas? why two heap_allocs? you should create a var to the outer lam, seems like you're creating a var to an unused place? - AI: You're right! The VAR(fV_loc) should point to the outer lambda's body location (outer_loc), not to some separate fV_loc. Is this correct? - Me: sounds ok-ish but please double check, you're the machine here - AI: You're right, let me trace through carefully... [traces through, verifies, fixes code] collapse_4 passes! [continues fixing APP, DRY, MAT, CTR cases with same pattern] All 35 tests pass!

@JungleSilicon I do something similar. I either make or find a beat on the internet. Record over it then let SUNO work

i've been really getting into writing songs on the piano, recording them and then getting suno to apply style transfer to them. i then go into midjourney, generate shots, turn them into videos and then compose it together into a music video. "what is lost"

@bdsqlsz Ah, I see... pretty cool... Is this hard to get?

@itsanderz I have the test qualification, on their app.