Building software with AI every day. I share the workflows and tools I use, what works, and what doesn't. SWE @GoDaddy
Vancouver, BC
Joined July 2009
- Tweets2.9K
- Following636
- Followers292
- Likes5.6K
jeez Astra is a beast, running it with medium effort feels so smooth, smart and fast at the same time
huge
We are committed to pushing the model frontier across cost efficiency, capability, and speed.
Starting today, we are reducing prices for GPT-5.6 Luna by 80% and GPT-5.6 Terra by 20% , and offering a faster option for GPT-5.6 Sol in the API.
Luna and Terra’s lower prices are reflected in how usage is counted in Codex and ChatGPT Work, so your usage goes further.
Cool job
We're hiring a Research Engineer at @Arsenal ⚽🔴⚪ to work directly with our Men's First Team!
We're building state-of-the-art AI models for the football domain. This role will focus on building the application layer for our research to advance coaching and analysis workflows.
Use Sessions to audit my past conversations and identify gaps, incorrect assumptions, and incomplete or inaccurate mental models in my understanding of this codebase: its architecture, domain model, business logic, boundaries, and current behavior.
Focus on misunderstandings that caused or could cause incorrect prompts, implementation mistakes, flawed designs, rework, or later corrections. Compare my expressed understanding with the current codebase; do not treat plans or historical claims as current behavior.
For each meaningful finding, provide:
- What I appeared to believe or misunderstand
- Evidence from the sessions
- How the codebase actually works, with code references
- The likely impact of the misunderstanding
- A concise, corrected mental model
Prioritize recurring and high-impact findings. Separate evidence from inference, note uncertainty or missing history, and avoid generic observations. Do not modify the codebase.
GPT 5.6 Sol 10 minutes after you tell it's overengineering things again: "A useful simplification emerged"
@ferueda retweeted
i'm slowly realizing that the code i'm writing is no longer code
traditionally when we build software, we write code. code tells the machines "here's what you do"
if we write wrong code, machines will do wrong things. and that's what we call a bug
earlier this month, i wrote a pretty bad bug into one of firstmate's bash scripts. the code literally can't run, and should have broken firstmate
except it didn't. it went unnoticed for days. i discovered it when i came across the code and spent minutes wondering how on earth this could work
i then found that the agent ran the script, saw it fail, figured out what the script was trying to do, and did a workaround to achieve the same goal
so a bug that should have crashed the whole software almost didn't have any visible impact
that's when i discovered that what i wrote in the bash script is no longer code. it's not "here's what you do"
it's intent. it's "here's what i want"
intent doesn't crash and can't be broken. it gets executed regardless whether it's "correct" or not. i can no longer write "bugs"
what can still happen in intent is what i call "misses", which could be -
1. a misalignment between what's written and what my real intent is - this happens when i fail at articulating my thoughts
2. a misalignment between my real intent and the real demand - this happens when i fail at understanding the world
those are becoming the most important human skills in this new era
