Barbarians at the Gate
The RJR Nabisco LBO — Wall Street dealmaking at its most cutthroat.
The most fun I've had reading about people behaving badly with other people's money.
Bay Area, California
Tyler
Darisme
Darisme
Computer Science @ SJSU · AI tooling, full-stack &
blockchain
I'm a CS student at San José State University who builds
at the intersection of AI tooling, full-stack web, and
blockchain. I care about shipping
working tools, not demos.
Projects
Accordion
202I built Accordion because an AI agent's context window is a black box — when it fills, content gets silently dropped. It turns that into a living visual map of every block the agent holds, letting you fold blocks to cached summaries, unfold them instantly, or pin critical ones the automated Conductor can't touch. On SlopCodeBench at a 100k-token budget, my Thermocline conductor scored 83.3% vs 33.3% for naive compaction — 2.5× at equal cost. 2nd place, UC Berkeley AI Hackathon 2026.
AfterCart
I built AfterCart at Davis Hacks 2026: photograph a grocery receipt and it OCRs every line item, then tells you what the same basket costs at nearby stores — matching against a crowdsourced database of 18,649 price observations across 244 stores, on Postgres 16 with PostGIS + pgvector, Google Vision OCR, and Gemini 2.5 Flash.
AceAnything
An AI quiz platform I built (FastAPI + Vue + Gemini) that generates adaptive quizzes on any subject with spaced repetition, instant explanations, and text-to-speech.
Automated-Game-Bot
A fully autonomous Albion Online bot I built with YOLOv11 detection, OpenCV, and PyAutoGUI; I trained and open-sourced five detection models and ran scanning/actions in parallel.
Blackjack-On-Chain
A decentralized blackjack dApp with seven modular smart contracts running all game logic on-chain, deployed on Arbitrum Sepolia.
Highlights
Awards & Contests
2nd — UC Berkeley AI Hackathon
1st — SJSU Programming Contest
Top 20 — ICPC Regional
3rd — DAHACKS 3.5
Experience
SWE Intern — Shipcaptain
Built a secure full-stack admin portal (Next.js 15, Prisma, PostgreSQL) with role-based access, audit logging, and NextAuth.
Blockchain Intern — Serraform Labs
Shipped the on-chain USDC payment contract for a live Web3 product on a 7-person team.
Tech Officer — Competitive Programming Club
Delivered weekly algorithms & data-structures lectures; mentored members on contest prep.
What I do
AI tooling & agents
I build tools that make LLM agents observable and
steerable.
Full-stack web
Next.js / React / FastAPI apps on Google Cloud Run.
Blockchain & smart contracts
Solidity dApps; on-chain game logic and payments.
Computer vision & ML
YOLO/OpenCV pipelines and applied Gemini/Claude.
Competitive programming
ICPC competitor; I teach weekly algorithm lectures.
Data & geospatial
PostgreSQL with PostGIS + pgvector for search and
matching.
who am I
The books I read, and the miles I run.
What I'm reading now
A Promised Land
Presidential memoir, volume one.
A reminder that big decisions get made with far less certainty than we assume.
Past reads
Breakneck
China's industrial policy & manufacturing.
Made me realize how much of 'the future' is really a manufacturing question.
Nexus
Information networks, AI, human coordination.
Best when it sticks to how information networks actually shape power.
Business Adventures
Classic Wall Street case studies.
The details of business change; the people in it never do.
Blitzscaling
Hypergrowth strategy.
A useful playbook — as long as you remember most companies shouldn't run it.
Atomic Habits
Habit systems.
The rare habits book where I actually kept a couple of the habits.
The Shock Doctrine
Disaster capitalism.
I don't buy every claim, but it changed how I read a crisis.
Poor Charlie's Almanack
Mental models.
Worth it for the mental models; Munger's bluntness is the bonus.
Zero to One
Monopoly thinking.
Half of it I disagree with, and I still quote it constantly.
Runner Frontier — My personal running log
I built Runner Frontier to turn PRs into a continuous frontier. I didn't want my progress to be defined only by arbitrary benchmarks like my one-mile, two-mile, or 5K times. I wanted to measure my improvement over time, in my own way. You can see a summary of my data in the cards below or look at the graph with the raw data here →.
Runner Frontier preview
Pace × distance, run by run
Open the live graph
2026 by month
Mileage / average paceJan17.8 mi9:41/mi avg
Feb19.8 mi9:09/mi avg
Mar26.0 mi9:21/mi avg
Apr32.2 mi9:05/mi avg
May27.7 mi9:45/mi avg
Jun42.6 mi10:17/mi avg
Jul36.3 mi10:20/mi avg
Personal records
All time1.0 mi · May 4
2.0 mi · Apr 18
3.3 mi · Apr 15
4.0 mi · May 2
10:50/mi · Jul 2
1.2 mi · 10:04/mi
10:17/mi · Jul 16
Latest entries
-
5.5 miles
- Time
- 56:48
- Pace
- 10:17/mi
-
4.1 miles
- Time
- 43:22
- Pace
- 10:39/mi
-
3.0 miles
- Time
- 31:00
- Pace
- 10:18/mi
-
4.5 miles
- Time
- 47:06
- Pace
- 10:27/mi