Tom "Plaetorius" Gernez

357 posts

Tom "Plaetorius" Gernez banner
Tom "Plaetorius" Gernez

Tom "Plaetorius" Gernez

@plaetorius

retard, autist, co-founder

San Francisco, CA 加入时间 Eylül 2024
61 关注56 粉丝
Polymarket
Polymarket@Polymarket·
NEW: A Mexican “Batman” has reportedly emerged in Jalisco, hunting motorcycle thieves & taping them to street poles.
Polymarket tweet mediaPolymarket tweet media
English
1.2K
5.3K
58.3K
3.3M
javi
javi@javiiarchive·
Turn your images and videos into ASCII art 👾 ❋ javii.tools · asciilab launched!
English
45
134
2.3K
125.7K
Tom "Plaetorius" Gernez
Tom "Plaetorius" Gernez@plaetorius·
@0xsakshamtyagi @paper do you know about ui-ux max pro for Claude Code? if yes, why @paper? i'm wondering, seeking for better tech I feel like ui-ux max pro always does the "same kind of design"
English
0
0
0
224
saksham.base.eth
saksham.base.eth@0xsakshamtyagi·
I still can't believe this whole landing page came out of just a conversation with Claude. I used @paper for prompts to design then back to code I mean this is crazyy 🫡
English
49
23
993
94.7K
Tom "Plaetorius" Gernez
Tom "Plaetorius" Gernez@plaetorius·
update: as an experiment i have purchased the domain yourideas.store and you can sell your ideas engineering is commoditized, so let's see if the world is ready for an idea marketplace (it's still in early beta, I'll roll it out for real if there is demand)
Alex@AlexanderTw33ts

update: as an experiment i have purchased the domain alex.store and am selling ideas for $5,000 each engineering is commoditized, so let's see if the world is ready for an idea marketplace

English
0
0
0
52
Kali B.
Kali B.@Kali_InRealLife·
@plaetorius C4 use to kick. If you’re ever looking for an alternative give Bucked Up a go.
English
1
0
1
3
Clavicular
Clavicular@Clavicular0·
I thought I did something wrong to upset people in France, but it turns out the French are impolite shitbags. No AC, terrible economy, horrible quality of living. Id be pissed too🤣.
Clavicular tweet media
English
8.2K
953
25.8K
14.4M
max
max@maxkolysh·
i polled a bunch of YC founders on how they got their first 10 customers. i was so surprised by the results that i made a video about it. enjoy!
Y Combinator@ycombinator

Many founders start their customer search with cold email, LinkedIn, and prospecting tools. But the first 10 customers rarely come from a tool. It starts somewhere else: your network, showing up in person, and a willingness to do things that don't scale. In this episode of Startup School, YC Visiting Partner @maxkolysh draws on dozens of YC founder stories to explain how to identify the right buyers, start conversations, and turn them into your first customers. 0:00 - Why the first 10 are different 0:54 - Where does your buyer actually spend their time? 2:45 - Customers 1–3: work your warm network first 4:20 - Get in the room 5:14 - Conferences and founder dinners 6:15 - Find where your customers complain online 7:30 - How to go outbound 8:35 - Frame outreach as advice 10:20 - Writing outreach that sounds human 13:15 - Recap: The first 10 come from you

English
33
47
776
155K
Tom "Plaetorius" Gernez
Tom "Plaetorius" Gernez@plaetorius·
@bouliboulibouli dans tous les cas, que le France le veuille ou non, l’Europe va faire des siennes pour pas que le nucléaire se développe sur notre sol
Français
0
0
0
1.4K
Tom "Plaetorius" Gernez
Tom "Plaetorius" Gernez@plaetorius·
When you look at it @TJR and @AlexHormozi have the same social media growth strategy "do so much volume it would be unreasonable for you not to be successful"
English
0
0
0
57
Tom "Plaetorius" Gernez
Tom "Plaetorius" Gernez@plaetorius·
@akshay_pachaar truth is: sometimes you want to ONLY have the HTML, not the screenshot, because some data is visually hidden but still appear in the code. That’s often the case for phone numbers, emails, addresses Great tool, but to be used wisely
English
0
0
1
257
Akshay 🚀
Akshay 🚀@akshay_pachaar·
Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: github.com/StarTrail-org/… Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.
Akshay 🚀@akshay_pachaar

x.com/i/article/2052…

English
133
837
6.7K
933.3K
parisbayarea
parisbayarea@parisbayarea·
I invited him to a hackathon
English
14
0
89
14.2K
Your MVP Guy
Your MVP Guy@Sherifdeenolat2·
What’s one common problem every founder should be prepared for?
English
43
1
29
1.8K
Jyri
Jyri@jyriso·
Drop your startup link. I need inspiration!
English
79
2
47
4.4K
Calvin Lim
Calvin Lim@calvinluvsrice·
What is everyone doing to find their first customer?
English
22
0
17
2.4K
Tom "Plaetorius" Gernez
Tom "Plaetorius" Gernez@plaetorius·
@calvinluvsrice LinkedIn outreach 100%. I had all of mine like this. It’s not that deep, just connect with people and send DMs like it’s a WhatsApp DM. They’ll answer
English
1
0
1
54
Tristan Rhee
Tristan Rhee@Tristanrhee3·
What's coming after artificial intelligence?
English
4.6K
269
3.3K
1M