Geremie Yeo

Some reflections from Deep Past competition. kaggle.com/competitions/d… We finished in 24th / 2673 with 85 submissions. I joined it with my colleague despite working past 11pm grinding for my startup for 6 days a week. I was ambitious and wanted to try something that seemed impossible: winning a gold with this little time, and test the hypothesis below.

it would be cheaper if I understood the data obviously😂

letting an agentic AI system generate the synthetic dataset for a competition "is a good idea" 🤣

TIL you can create architecture diagrams in README.md on github within ```mermaid

LMAO I really thought Gemini was not following instructions until I realised I had a stale addition to the prompt in a string which I forgot to remove

beautiful - visualizing Qgentic traces

this comp lmao, metric fix after metric fix

Codex is unusable with all these cybersecurity risk flaggings - I am getting them every 5 mins now 🤨

don't give up! 🤖

now Qgentic has an advantage - it won't stop regardless what happens

???

so Claude Code's file edit tool is just find-and-replace, not applying GitHub-style patch strings

@Clara_Gold The "deadlock" analogy feels very relatable lol

6 months ago, I moved to San Francisco. It’s the best place in the world to build, and one of the worst places to stay human. My unfiltered take: 1. SF is both overhyped and underrated The overhyped part: there are a lot of people with incredible resumes who are deeply unimpressive in real life. They were at the right company, at the right time, in the right market, and got carried by the wave. They made money, got comfortable, and now spend their time “exploring opportunities” over coffee, wasting your time. The underrated part: the top 1% here is insane. But almost impossible to get. Hiring in SF feels like being a guy on a dating app: everyone you want is out of your league, and everyone in your league wants someone out of theirs. The best people have unmatchable packages, endless options, and are optimizing for maximum impact: labs, frontier companies, or startups raising $100M pre-seed rounds. If you raised $10M from Tier 1 investors, you’re not hot shit here. You’re a B-player. It’s humbling. 2. There are fewer mission-driven people than I expected Especially on the application layer. A lot of people are in “secure the bag before it’s too late” mode. And honestly, it gives me the ick. The real religious builders I’ve met are often in labs, hardware, biotech, deeptech, defense — places where the work is hard enough that you can’t fake obsession. 3. The status game favors builders This is what SF does better than anywhere else. It rewards obsession. It rewards weirdness. It rewards people who make building their entire personality. Europe punishes that. SF gives it status. If you’ve felt like an outsider your whole life because you care too much, work too much, think too radically, or refuse to be chill about things that matter, this city will make you feel less insane. 4. The market liquidity is absurd Even if you don’t build a billion-dollar company, if you manage to build a strong product with a great team, someone smart might still acquire you for $ 100M. Yeah I know, it’s not your dream outcome as a founder, but on the days you feel desperate, it helps to keep going. 5. SF does not care about the meaning crisis that’s coming Anyone paying attention here can feel that something massive is happening with AI. But I’m shocked by how little people talk about the meaning crisis coming next. Everyone wants to talk about AI liberating humanity. Almost no one wants to talk about what happens when work — the thing that gives most people identity, structure, dignity, status, and purpose — starts disappearing. The vacuum will not be peaceful. People are underestimating the chaos that comes from humans suddenly having no idea why they matter. And I really feel like no one cares. 6. Personally, I’ve never been more unhappy I moved to SF and entered the matrix. I’ve always been intense. I’ve always worked crazy hours. But here, I lost the last parts of myself that were not about building. I don’t go to events. Most networking events feel like theater for people pretending to be important. The only events worth going to are small, curated dinners with people who are actually alive. I’ve made 0 real friends. I don’t do well with transactionality. I don’t do well with people constantly performing greatness. I don’t do well with rooms where everyone is optimizing and no one is being honest. So yes, SF is lonely, transactional, delusional, addictive, inspiring, boring, extraordinary, and completely insane. But it is still the only place to be right now if you’re a founder trying to build the next wave of humanity. And for now, that’s enough.

I see how painful it is to run a Developer subagent one at a time

I'm gonna record a real demo of Qgentic once I fix issues 268 and 221 in the Github. It needs those since Codex and Claude Code have them and they are one of the most productive features for me github.com/bogoconic1/Qge… github.com/bogoconic1/Qge…

so many Supabase transient errors these days 😭

its very funny how Codex usage limits drain much slower than Claude Code usage limits

@JiweiLiu nice work! I was drafting something similar when I refreshed and saw it was already posted. Need to be faster in the future...

Our kaggle agent is getting close to perfect score but it is too good to be true. We let our agent checked its own submission in light of the incoming metric update and write this audit post: kaggle.com/competitions/n…

Too many bugs 🤣 Perfect score (25/25) in 235/400 tasks. Total 5875. Codex and Qgentic working hard while my CC usage is low

Running Qgentic overnight 👍👍👍 it discovered

WTF this has to be the most broken software at this point 😂😂 25/25 for a task in NeuroGolf 2026