Not to fangirl, but Iโve gotten the best #AICoding results by telling one instance of Codex to code like they are @dhh (DRY, expressive, self-documenting, etc.) and another instance to review the work like DHH deciding if a PR should make it to Rails core.
Reviewer is merciless.
2. I have a few Codex prompts that make all this a breeze:
/dhh-linear-coder
- Sends the DHH bit
- Pulls a Linear issue based worktree name
- Reads the project
- Thinks about a plan
- Calls Gemini 2.5 Pro & Opus for feedback on its plan
- Saves plan in a md file named for issue
3. In a 2nd Codex instance, same dir:
/dhh-linear-plan-review
- Fetches issue from Linear again (Linear MCP)
- Scans project
- Reads the md (named after dir in ./planning/)
- Provides savage feedback in the md file
Back to 1st instance:
/read-plan-feedback
- You know the rest
OpenAI learned nothing from the Pepsi Challenge and Cola Wars of the 1980s
Poorly-contextualized marketing data & product feedback can lead you to make the wrong decision.
People prefer a taste of something sweeter in small amounts, but will always end up buying the real thing.
Weโve rolled back last week's GPT-4o update in ChatGPT because it was overly flattering and agreeable. You now have access to an earlier version with more balanced behavior.
More on what happened, why it matters, and how weโre addressing sycophancy: openai.com/index/sycophancy-โฆ
So OpenAI learned nothing from the Pepsi Challenge and Cola Wars of the 1980s?
People prefer a taste of something sweeter in small amounts, but will always end buying the real thing.
Weโve rolled back last week's GPT-4o update in ChatGPT because it was overly flattering and agreeable. You now have access to an earlier version with more balanced behavior.
More on what happened, why it matters, and how weโre addressing sycophancy: openai.com/index/sycophancy-โฆ
Iโve been using @cursor_aiโs coding agent really heavily for about a month. Itโs not perfect, but itโs directionally mind-blowing. But you have to do it a certain way or it takes more time than it saves. Whatโs working for you?
#AIAgents#Coding#Cursor
Regardless of who you think won the debate last night, JD Vance is the first vice presidential candidate in US history that doesnโt know who won the last presidential election. Itโs an embarrassment. #Debate2024 #