* at the end indicates that a task was rolled over from a previous day

day 1 (1/4)

• verify mmmlu is unclaimed (check prime-environments and research-environments and PRs)
• check if mmlu-pro is claimed—it is, it's in research-environments
• understand mmmlu schema
• scaffold environment structure

extra credit

• build web tracker for work log

day 2 (1/5)

• implement mmmlu environment (dataset loading with language/subject filtering)
• test locally with vf-eval

extra credit

• add manifold market widget to web tracker

notes

• implemented the basic environment, but i didn't get through language and subject filtering

day 3 (1/6)

• language and subject filtering*
• clean up code, write docs
• generate required outputs for pr
• submit pr
• share pr in pi discord

notion mcp bounty + application prep

day 4 (1/7)

• deep-read notion api docs
• review existing notion mcp server (https://github.com/modelcontextprotocol/servers)
• sketch simulator architecture: what state needs to be maintained?

day 5 (1/8)

• draft list of 30+ task ideas across API capabilities
• set up project structure
• leetcode (1 problem)

day 6 (1/9)

• implement core state model (in-memory or sqlite)
• build basic api endpoints (create/get page)

day 7 (1/10)

• continue api endpoints (update/delete page)
• leetcode (1 problem)
• check mmmlu pr and respond to feedback

day 8 (1/11)

• implement database operations (create db, query, add row)
• leetcode (1 problem)

day 9 (1/12)

• add block operations (notion's content model)
• prepopulate with realistic sample data
• leetcode (1 problem)

day 10 (1/13)

• add search functionality
• check mmmlu pr and respond to feedback
• leetcode (1 problem)

day 11 (1/14)

• begin writing task set with success criteria (target: 15 tasks)
• write verifier logic for completed tasks
• leetcode (1 problem)

day 12 (1/15)

• continue task set (15 more tasks, 30 total)
• continue verifier logic
• leetcode (1 problem)

day 13 (1/16)

• begin prime-rl integration
• research open roles at pi, anthropic, other targets
• leetcode (1 problem)

day 14 (1/17)

• continue prime-rl integration
• draft pi job app materials
• check mmmlu pr status

day 15 (1/18)

• finish prime-rl integration, get a training run working
• leetcode (1 problem)

day 16 (1/19)

• run training, document results
• clean up code, write documentation
• leetcode (1 problem)

day 17 (1/20)

• submit notion bounty pr
• post in pi discord
• submit pi job app

apps + interview prep

day 18 (1/21)

• submit anthropic apps
• leetcode (1 problem)
• ml review (skim attention mechanism, transformer architecture; refresh, not deep study)

day 19 (1/22)

• submit 2 more apps (deepmind, redwood, mechanize, imbue, cohere)
• leetcode (1 problem)
• check both prs, respond to feedback

day 20 (1/23)

• prep your narrative, practice explaining mmmlu/notion work out loud
• leetcode (1 problem)
• follow up on pi application if no response

day 21 (1/24)

• submit 2 more apps
• leetcode (1 problem)
• ml review (rl basics, policy gradient, reward shaping)

day 22 (1/25)

• review own prs (anticipate questions about design decisions)
• leetcode (2 problems)
• behavioral prep: pick 3 amazon stories that translate to ai lab context

day 23 (1/26)

• practice system design (design a distributed rl training system)
• leetcode (2 problems)
• prep questions to ask interviewers

day 24 (1/27)

• adjust plan based on layoff outcome
• leetcode (1 problem)
• check all app statuses

buffer + consolidation

day 25 (1/28)

• address pr feedback
• submit 1-2 more apps if needed
• leetcode (1 problem)

day 26 (1/29)

• if prs not merged, ping reviewers
• schedule interviews that have come through
• leetcode (1 problem)

day 27 (1/30)

• interview prep (practice coding while explaining thought process)
• review all application statuses
• leetcode (1 problem)

day 28 (1/31)

• draft february plan based on what's in motion
• leetcode (1 problem)