Sabitlenmiş Tweet
Ilya Pivto
3.7K posts

Ilya Pivto
@ipivto
AI content + distribution for brands & apps that need to grow fast. Building https://t.co/bjHXSWe2Ty (content) • https://t.co/XNt9z0qfeI (creator marketplace)
Katılım Nisan 2024
128 Takip Edilen347 Takipçiler

I'm 100% Codex pilled now
Been using Codex and Claude Code side by side hours a day for 2 months straight
No longer using them side by side. Codex has become incredible
What did it for me is the self testing. Every change it makes it self tests in it's own browser
I went from about 40% of my changes being buggy on first go to at most 3% maybe? So much more reliable and allows me to get in an awesome flow state
Listen, Claude can literally drop an update tomorrow that changes all of this, but for now I'm really blown away by Codex
Do yourself a favor and don't have loyalty to any company. Use every tool. Use whatever is the best at the moment. Switch whenever they're no longer the best. No point in tribalism
But at the moment I'm REALLY enjoying my time with Codex
English

Figma-to-video is real now (GitHub repo)
we just open-sourced VibeMotion-1 (pre-alpha):
the video editing tool that can
> auto-edit your videos
> import your Figma frames + all layers
> animate layers by prompt
> animate images using LTX-2.3 AI model (local, open-sourced)
all on the classical editing timeline
github link 👇
AI Pulse@youraipulse
Vibe coding was just the start. Now comes VibeMotion VibeMotion: a local AI video editor where you can > describe motion in plain text > import Figma frames > and build animations without After Effects or DaVinci No complex software Just describe it → get motion GitHub link below 👇
English

@sha_zdiii conceptually it is not complicated - connect existing powerful LLMs to a tool (& maybe a proxy layer to simplify the i-face)
English

@ipivto AI agents editing full videos feels like the next big shift
English

Every short-form video eats 3 hours of editing for 30 seconds of output. That ratio has bothered me since I started making more of them.
So I built an AI agent that edits videos as I would do.
Connect your claude code, codex, hermes, etc and it will drive the process.
First real test: this hoodie commercial. One prompt.
English

@EBogomolovs yes, it's a lot of watching & deciding. I plan to connect vision capabilities of a model to it - should improve it a lot.
I made 3 attempts with this prompt but only because of bugs, not because of claude being dumb.
English

@ipivto The 3h isn't really edit time. It's watching the cut back and deciding it's wrong, then trying again. The agent collapses the clicking. Taste calls are where the hours actually go. How many takes did one prompt produce before you kept this one?
English

@Just_sharon7 frontier models are smart enough now to one shot such edits
English

The agent does all the heavy lifting:
• Loads footage & cuts it
• Adds texts with scalable typography sizes & positions across 9:16 / 16:9
• Amazing job with keyframes (zooms, transforms)
• Blur effect with intensity tokens
• Image & video overlays
Still early, many more features are planned.
It's limited only by the underlying video editor, which is super powerful.
Should I opensource it?
English

@gregisenberg very useful insights, makes me feel that tech is not that doomed as I imagined
English

I just got back from SF and I FEEL INSPIRED.
I spent 5 days with frontier AI model teams, AI startup founders, and 3 billionaires.
My takeaways:
1. I had lunch with 3 billionaires. All of them are buying SaaS companies and rebuilding them agent-first. They were deeply inspired by Bending Spoons and Ryan Cohen's eBay deal. Buy the company, cut the headcount, rebuild the tech, add agents, add features, make more valuable experience, raise prices.
2. The frontier model companies are hungry for usage data from the field. They can see API calls and token counts. They can't see the actual workflows. If you're deep in a niche using these models in ways the model companies haven't seen, that understanding is incredibly valuable. Usage intelligence is the new alpha.
3. Consumer AI is massively underbuilt. Every billboard in SF is either B2B inference infrastructure or vertical agent companies. The entire city is optimized for enterprise. Meanwhile you have companies like Cal AI doing $50M ARR in 18 months as a consumer app. I met with a cool few teams doing consumer AI (@paulscherer / @ekuyda)
4. MCP came up in literally every conversation. The companies exposing their product as MCP endpoints are getting pulled into deals they never pitched for. The ones that aren't are becoming invisible to agents. This is the new SEO. If agents can't find you, you don't exist. Building products for agents is the new zeitgeist in general.
5. Not uncommon for hot seed rounds to be $25-50 million valuations. I saw a Series A at $450 million
6. If I had a dollar every time someone mentioned "forward-deployed engineer" this trip I could have funded a seed round. It's the hottest role in SF right now. The person who sits between the agent and the customer, making sure everything actually works.
7. The mood around open source shifted. A year ago it felt like open source was chasing the frontier models. Now founders are telling me Gemma and DeepSeek are good enough for 80% of what they need at a fraction of the cost. The "which model do you use" conversation is being replaced by "which model for which task." Model loyalty kinda feels dead.
8. Voice agents came up more than I expected. Multiple founders told me voice is the interface for the next billion users. The billion people who will never type a prompt will absolutely talk to one.
9. The Obsidian community in SF is weirdly intense. Multiple founders showed me their vaults unprompted. Like showing someone your home gym. It's a flex now. The quality of your knowledge base (second brain?) is becoming a status symbol among builders.
10. Maybe it was just the people I met but the age of the founders is shifting. I met more founders over 40 this trip than any trip before and more founders under age 21 than ever before. Founders getting older and younger at the same time.
11. I spoke to a lot of fast-growing startups, VCs and frontier models who are hiring content creators right now.
12. The restaurant scene in SF is actually better than it's been in years. Founders are going out more. Alcohol is out, not surprisingly.
13. SF doesn't feel like the only place anymore. We all have access to the same frontier models. We all read the same X feed. A founder in NYC or Lagos is calling the same APIs as a founder in SoMa. So in the past it felt like SF was always lightyears ahead, doesn't feel that way anymore. It's okay not to live in SF and have BIG DREAMS.
14. The coworking spaces in SF are half empty but the coffee shops are packed. People want to be around people. I had a few startup ideas here....
15. Walking around the Mission I noticed something: the street-level businesses, the taquerias, the barbershops, the laundromats, none of them use any AI at all.
16. I heard the phrase "agent debt" for the first time. Like technical debt but for agents. When you hack together an agent workflow fast and never clean it up, the system prompts conflict, the memory gets polluted, the tools overlap. 6 months later the agent is doing weird things and nobody knows why lol.
17. Met a few people who carry two phones now. One for personal. One that's basically an agent terminal running Telegram or iMessage connections to their agent fleet.
It's always amazing to get that dose of inspiration in SF. I FEEL INSPIRED.
But I'm so happy to be back home, locked in and building.
We're 12-18 months into a shift that will take 15 years to play out. The urgency in every conversation was real.
What an incredible time to be building.

English

@PositivFuturist i wonder if anybody from the vibe coding culture actually understands what 's happening here.
English

@mike_matas the promo is fantastic. would be cool if you made a breakdown of the workflow you made it with.
English

clothing brand promos made with ai are getting crazy views specifically on insta right now
Abdul Șhakoor@abxxai
Making a commercial North Face ad using GPT Image 2 x Seedance 2.0 on @dreamina_ai Save this — full prompt below 👇
English

@HeyAbhishek As this kind of Ghibli style? previously there were IP issues
English

@oragnes What about languages? I have seen there are models that can translate from animal languages :)
English

@maxescu So before kling motion control was the best for cloning videos. Is it Gemini Omni now?
English

Add anyone to the Backrooms with Gemini Omni.
Prompt:
Keep the subject's motion and timing exact. Place the subject in the Backrooms: yellow patterned wallpaper, damp musty carpet, low ceiling, identical fluorescent panels overhead, the space extends in every direction without end. The subject seems unaware they are lost. Camera feels found-footage adjacent.
English

Some new improvements to performance just went in.
Python gets a bad wrap for performance but we aint looking to shabby against a trillion dollar co's rust codebase, beating codex at most multi-turn tasks we benchmarked (mt stands for multiturn)
PR: github.com/NousResearch/h…

English









