Filip Michalsky

805 posts

Filip Michalsky

Filip Michalsky

@FilipMichalsky

AI Builder passionate about innovation, strategy, and giving back.

NYC, USA Katılım Mart 2021
291 Takip Edilen412 Takipçiler
Rachael Horwitz
Rachael Horwitz@RachaelRad·
Hello. Reminder as you think about compliant on and off ramps etc: @Airwallex is not a payments app layered on top of existing rails. It is a vertically integrated global financial infrastructure company that spent ~10 years building (and licensing) its own proprietary money-movement network from scratch. It owns the end-to-end stack in a way that most US fintechs simply don’t because building that outside the US is brutally hard and capital-intensive.
English
9
0
50
6.7K
Hero Market
Hero Market@HeroMarketHQ·
The prediction market for people building consumer brands. Trade YES/NO on launches, M&A, retail wins. Play money. Real signal. Closed beta is open. Request access → heromarket.com
English
1
1
3
2.5K
Filip Michalsky
Filip Michalsky@FilipMichalsky·
Every Friday I wish I had more compute for the upcoming weekend
English
0
0
0
16
Filip Michalsky
Filip Michalsky@FilipMichalsky·
I had a lot of fun talking about what we are building at @paywithsoap , the future of AI enabled payments infra, how are we thinking about stablecoins, and more! Thanks for having me @BettingStartups
BettingStartups.com@BettingStartups

🚨 New episode alert @jesselearmonth is joined by @FilipMichalsky from @paywithsoap, an AI-native orchestration layer designed to simplify the complex payments stack for real-money gaming operators. Full episode 👇 ▶️ YouTube: youtu.be/1NCvaK84RIw ⚪️ Apple: podcasts.apple.com/us/podcast/ep-… 🟢 Spotify: open.spotify.com/episode/0jOaqv…

English
0
0
0
36
eric
eric@defyneric·
onchain private credit is the next $100B opportunity whoever can issue credit with low default rates and strict payment reinforcement policies controls the next generation of banking hint hint.. @FlexSuperApp
English
5
0
36
6.7K
Filip Michalsky
Filip Michalsky@FilipMichalsky·
Yess the mythos moment for form filling is finally here - do you know how many financial forms we need to fill out on daily basis as a payments infra company? Excited for this @browserbase
Ronin@DeRonin_

Do you understand what Browserbase just open-sourced??? an agent that learns any website once, then does the job 10x cheaper forever [ literally how it helps me ]: - writing scrapers for new sites (used to spend half a day per site, every single time) - chasing selectors when sites redesign on a tuesday (lost weeks to this) - digging out hidden APIs buried in network traffic (gave up on this too many times) - explaining to my team HOW the agent does the job (was impossible until now) Autobrowse figured all of that out by itself in 3-5 iterations and saved the answer as a markdown file the next agent reads BEFORE it starts [ how it actually works ]: > give the agent a real task on a real site > it tries, fails, learns, tries again > 3-5 rounds and it converges on a path that just works > writes that path down as SKILL.md > next agent loads it and skips straight to the answer the markdown file IS the memory every browser agent before this had AMNESIA figured out the site, then forgot the second the session closed you've been paying the same discovery tax 100 times in a row.. and not noticing [ Karpathy's auto-research idea, but applied to the web ]: same idea, just different approach Karpathy did it for research and coding loops Autobrowse does it for the open web the new part: Karpathy's loop got smarter inside ONE session Autobrowse SAVES the lesson into a file the next agent reads before it even starts iteration = graduation the agent doesn't just learn.. it leaves a note for every agent that comes after [ the math ]: Craigslist scrape: - generic agent loop: $0.22 / 71 seconds - graduated Autobrowse skill: $0.12 / 27 seconds form-fill task: - run 1: $1.40 - run 4: $0.24 run 1 pays for everything that comes after [ the part that broke my brain ]: they pointed it at a federal grants portal agent dug around and found an undocumented JSON endpoint humans had missed for years a 28-page scrape collapsed into one fetch > an agent tried something a person never would > and found something a person would never see.. 100% OPEN SOURCE, FREE I was digging inside of it for the whole morning and got impressed when I saw such as savings on tokens spending literally for scraping 10 websites, I spent just 12 cents instead of basic $1.02 P.S. Sorry if somewhere my reaction was too "forcing" to setup it, just wanted to mark by BOLD what's the treasure you can skip this, it's your deal ❤️

English
0
0
0
69
Filip Michalsky retweetledi
Ronin
Ronin@DeRonin_·
Do you understand what Browserbase just open-sourced??? an agent that learns any website once, then does the job 10x cheaper forever [ literally how it helps me ]: - writing scrapers for new sites (used to spend half a day per site, every single time) - chasing selectors when sites redesign on a tuesday (lost weeks to this) - digging out hidden APIs buried in network traffic (gave up on this too many times) - explaining to my team HOW the agent does the job (was impossible until now) Autobrowse figured all of that out by itself in 3-5 iterations and saved the answer as a markdown file the next agent reads BEFORE it starts [ how it actually works ]: > give the agent a real task on a real site > it tries, fails, learns, tries again > 3-5 rounds and it converges on a path that just works > writes that path down as SKILL.md > next agent loads it and skips straight to the answer the markdown file IS the memory every browser agent before this had AMNESIA figured out the site, then forgot the second the session closed you've been paying the same discovery tax 100 times in a row.. and not noticing [ Karpathy's auto-research idea, but applied to the web ]: same idea, just different approach Karpathy did it for research and coding loops Autobrowse does it for the open web the new part: Karpathy's loop got smarter inside ONE session Autobrowse SAVES the lesson into a file the next agent reads before it even starts iteration = graduation the agent doesn't just learn.. it leaves a note for every agent that comes after [ the math ]: Craigslist scrape: - generic agent loop: $0.22 / 71 seconds - graduated Autobrowse skill: $0.12 / 27 seconds form-fill task: - run 1: $1.40 - run 4: $0.24 run 1 pays for everything that comes after [ the part that broke my brain ]: they pointed it at a federal grants portal agent dug around and found an undocumented JSON endpoint humans had missed for years a 28-page scrape collapsed into one fetch > an agent tried something a person never would > and found something a person would never see.. 100% OPEN SOURCE, FREE I was digging inside of it for the whole morning and got impressed when I saw such as savings on tokens spending literally for scraping 10 websites, I spent just 12 cents instead of basic $1.02 P.S. Sorry if somewhere my reaction was too "forcing" to setup it, just wanted to mark by BOLD what's the treasure you can skip this, it's your deal ❤️
Ronin tweet media
Kyle Jeong@kylejeong

x.com/i/article/2051…

English
66
144
2.1K
313.9K
Filip Michalsky retweetledi
Zecheng Zhang
Zecheng Zhang@zechengzh·
Introducing Mirage, a unified virtual filesystem for AI agents! 6 weeks. 1.1M+ lines of code. We rewrote bash from the ground up so cat, grep, head, and pipes work across heterogeneous services. S3, Google Drive, Slack, Gmail, GitHub, Linear, Notion, Postgres, MongoDB, SSH, and more, all mounted side-by-side as one filesystem. Bash that AI agents already know works on every format! cat, grep, head, and wc parse .parquet, .csv, .json, .h5, even .wav! One pipe can stitch S3, Drive, GitHub, Slack, and Linear together, same Unix semantics throughout. Workspaces are versioned too. Snapshot, clone, and roll back the whole thing with one API call. A two-layer cache turns repeated reads into local lookups, so agent loops stay fast and cheap. Drop a Workspace into FastAPI, Express, or a browser app. Wire it into OpenAI Agents SDK, Vercel AI SDK, LangChain, Mastra, or Pi. Run it alongside Claude Code and Codex. Site: strukto.ai/mirage GitHub: github.com/strukto-ai/mir… #AIAgents #OpenSource #AgenticAI #Strukto #Filesystem #VFS
Zecheng Zhang tweet mediaZecheng Zhang tweet media
English
171
337
3.3K
614.1K
Filip Michalsky retweetledi
Ramp Labs
Ramp Labs@RampLabs·
We partnered with @PrimeIntellect to build Fast Ask, a small RL-trained subagent that helps our Sheets agent find answers in spreadsheets. It scores +4% over Opus on exact match accuracy at Haiku latency.
English
27
49
734
324.4K
Filip Michalsky
Filip Michalsky@FilipMichalsky·
@ariG23498 Its the deterministic code for looping inference in & out of the model. We will witness the day when the agent writes its own harness but the day is not today (could be tomorrow afaik)
English
0
0
0
23
Aritra 🤗
Aritra 🤗@ariG23498·
What do you mean by the terms "harness" and "scaffold" in the context of agents? I have heard a lot of explanations while I was at ICLR, but I could not understand why they did not converge to a sinlge explanation. For me: harness -- the utilities that we provide an agent, which includes the system prompt and the tools available (analogy would be a real harness that is tied to constraint something) scaffold -- the same as harness
English
9
1
24
4K
Filip Michalsky
Filip Michalsky@FilipMichalsky·
Just heard an AI agent pitch on nyc subway - this is either the top or that founder is really hustlin bustlin
English
0
0
1
112
Sarah Chieng
Sarah Chieng@MilksandMatcha·
The absolute lack of taste in this city is abominable. The Devil Wears Prada 2 is a ruthless education in beauty, aesthetics, and taste. We're renting out an entire theater on opening night so the researchers training our models can get educated themselves. Comment “PURPLE GRADIENT” and I’ll DM you the invite.
Sarah Chieng tweet media
English
49
1
80
18K
Filip Michalsky retweetledi
Meltem Demirors
Meltem Demirors@Melt_Dem·
two ten trillion dollar industries forming machine god - AI human god - peptides love to see it
English
26
17
268
24.4K
Filip Michalsky
Filip Michalsky@FilipMichalsky·
Low key we think we got some job candidates like this with AI Deepfakes / lip sync / voice over claiming to “live in Romania” - fortunately their models are not good enough so we could tell still
TBPN@tbpn

CrowdStrike CEO @George_Kurtz says North Koreans are posing as American employees to gain access to company laptops, which are then sent by a mule to laptop farms run by the North Korean threat actor group Silent Chollima. "The laptop that you send them gets sent somewhere in the US to a mule, and that mule takes it to a laptop farm. Then the North Koreans control it and bypass all of your security because you just handed them a laptop." "We first started notifying customers, saying, 'Hey, we think it's not really Bob in Texas working for you. It's a North Korean.' They said, 'Yeah, you're right,' and went to the hiring manager." "They told the hiring manager, 'Hey, we need to get rid of this person. It's a North Korean.' And his response was, 'Well, they do really good work. Can we keep them?'"

English
0
0
0
94
Filip Michalsky retweetledi
jason
jason@jxnlco·
Heard that Elon is trying to rename cursor to xcode
English
278
176
5.3K
371K