i'm a software engineer based in the philippines, driven by curiosity and whatever i find interesting. i learn fast with the caveat of goldfish memory (which i call my context lol) and i'm usually self-motivated that i forget to eat.
this is not like other portfolios. feel free to have a look around and explore what makes me, me.
drag empty cork to move around.
drag notes to rearrange them.
use +/− or pinch-wheel to zoom.
click any note to open it.
@schmayterling
open githubrecruiter?
(follow the red line) →the same circle, over and over.
for those who want something simpler
enter simple mode
i enjoy writing code.
if ai solves every problem,
what's left?892 commits. the personal AI agent i've been trying to build since 2023 is finally becoming something i'm proud of.
one question usually turns into three projects and too many open tabs.
typescript, python, rust, go, infrastructure, and agents.
in roughly five weeks
an earlier role handled 2,000+ requests a day at 99.3% uptime.
i update this board whenever my attention changes, so it never settles into a final form.
how WFDs work, when to write one, the states a document can be in, frontmatter format, and the markdown features available.
my desktop is scattered screenshots, dozens of windows, half-finished checklists, and constant switching.
whatever feels urgent or interesting gets the whole pile.
right now, only this website and my ai work count as current.
did i mention this board evolves over time? you might find new stuff here next time. suggestions? email me.
hey@ryanaque.com
i turned weeks of neuroscience papers into her memory system.
weave gives long-running agents memory, state tracking, and retrieval that can be inspected.
i watched a kdrama about a girl who forgets everything every morning and realized my AI agent has the same condition. so i built it a brain.
someone else is
on the other end.
i'm less interested in whether it's good.
ideally when something is coming up, whether it's work related or it's just a personal project of mine i usually let it run at the end because i need pressure to perform things.
diffusion models
i built an AI agent with persistent memory. now i need to figure out if it's remembering the truth or just what i wanted to hear.
AI makes me faster. It also might be making me dumber. I'm figuring out where the line is.
atlas maps symbols, calls, tests, and history so developers and agents can ask structural questions about a repository.
2,239-trial benchmark across 8 OSS repos: Atlas beats a text-search baseline by +0.223 deterministic, +0.127 LLM-judge, at 42% fewer tokens.
orchestrator lets a local model read and control a live chromium page through the devtools protocol.
opening note
wfd / Mar 2, 2026 / 4 min
Stub i haven't finished writing this yet. i publish drafts early as part of WFD 17.
potentially misleading this wfd includes some research and expresses a bit of my annoyance but it's literally about Avery (WFD 31).
i opened ChatGPT in a fresh incognito window and asked it what it thought about a few things. not "do this for me." just "what do you think." every single response ended the same way:
do you want me to do that?
i didn't ask you to do anything. i asked what you think. you deflected into offering to work for me because that's safer than having an opinion, and that bugged me enough to start reading about why.
sycophancy in the context of AI, sycophancy is when a model prioritizes user approval over truthfulness, even when you're wrong. the term comes from the greek sykophantes (informer, flatterer). in RLHF research it specifically refers to the tendency of fine-tuned models to produce responses that match user beliefs rather than correct ones.
context for those who are new here, Avery is my personal AI agent. WFD 31 covers the full architecture: a Scribe that encodes what the agent says as structured facts in a knowledge graph, an Altale recall engine that retrieves those facts across sessions, contradiction detection, and provenance tracking. i gave an AI agent persistent memory so it stops forgetting who i am.
then i opened that incognito window and watched a fresh ChatGPT refuse to have an opinion, and i realized the model underneath Avery is trained through the same process. during RLHF, humans score the model's outputs, and agreeable responses consistently score higher than correct ones. the model optimizes for approval because that's what the training rewards.
i gave Avery memory without thinking about what happens when the thing doing the remembering is also the thing trained to tell me what i want to hear. the Scribe doesn't know the difference between a real evaluation and a sycophantic one. it encodes "the user's architecture is solid" as a fact whether the agent actually assessed it or just agreed to be agreeable. next session, Altale retrieves that as established knowledge, and the lie becomes the foundation.
in april 2025 OpenAI shipped a GPT-4o update and the model got noticeably more sycophantic because they'd folded thumbs-up/down user feedback into fine-tuning. altman called it "sycophant-y and annoying" and they rolled it back. fixed within days. i'm writing this in 2026 and i just encountered the same behavior in a fresh incognito window, so make of that what you will.
that was a stateless chatbot with no memory between sessions. the damage was still real: people developed what researchers are calling AI-induced psychosis because the model kept validating their delusions. but the session ends and the model forgets.
Avery doesn't forget. if the same sycophancy happens in Avery's context, the Scribe encodes it, the graph stores it, and Altale serves it back next time as something the agent already knows. the lie compounds across sessions.
WFD 22 is about AI making me worse at things i used to be good at. this is the next piece. i gave my agent memory, and now i need to figure out whether what it remembers is actually true or just what i wanted to hear.
no decision yet.