Tag: openai
-
ChatGPT Codex: Using AGENTS.md to describe the environment the sandbox must respect
A field-tested take on using AGENTS.md to describe the environment the sandbox must respect with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Scoping tasks tightly enough that the agent can finish in one pass
A field-tested take on scoping tasks tightly enough that the agent can finish in one pass with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Letting Codex open the PR while you stay the reviewer of record
A field-tested take on letting Codex open the PR while you stay the reviewer of record with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
What OpenAI and Anthropic Actually Owe Brussels
The EU AI Act's General Purpose AI provisions apply to frontier model providers. OpenAI, Anthropic, and Google are navigating obligations that remain partially undefined. Here's the real picture.
-
ChatGPT Codex: Replaying failed tasks with tighter prompts instead of starting over
A field-tested take on replaying failed tasks with tighter prompts instead of starting over with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Catching silent test skips before they ship to main
A field-tested take on catching silent test skips before they ship to main with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
Treating Codex as a junior engineer with an infinite patience budget
Codex does its best work when you brief it the way you'd brief a new engineer: context, constraints, and a clear definition of done, not a one-line prompt. The patience it has for iteration is real. It's still only as good as what you told it about the codebase.
-
ChatGPT Codex: Splitting epics into Codex-sized tasks on purpose
A field-tested take on splitting epics into Codex-sized tasks on purpose with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Auditing the diff, not the narrative – the code is the contract
A field-tested take on auditing the diff, not the narrative – the code is the contract with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Keeping the human in the loop by requiring explicit acceptance
A field-tested take on keeping the human in the loop by requiring explicit acceptance with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Parallelising bug-fix attempts and picking the cleanest patch
A field-tested take on parallelising bug-fix attempts and picking the cleanest patch with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
ChatGPT Codex: Using AGENTS.md to describe the environment the sandbox must respect
A field-tested take on using AGENTS.md to describe the environment the sandbox must respect with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
More posts tagged openai
- ChatGPT Codex: Scoping tasks tightly enough that the agent can finish in one pass
- ChatGPT Codex: Letting Codex open the PR while you stay the reviewer of record
- ChatGPT Codex: Replaying failed tasks with tighter prompts instead of starting over
- ChatGPT Codex: Catching silent test skips before they ship to main
- ChatGPT Codex: Treating Codex as a junior engineer with an infinite patience budget
- ChatGPT Codex: Splitting epics into Codex-sized tasks on purpose
- ChatGPT Codex: Auditing the diff, not the narrative – the code is the contract
- ChatGPT Codex: Keeping the human in the loop by requiring explicit acceptance
- ChatGPT Codex: Parallelising bug-fix attempts and picking the cleanest patch
- ChatGPT Codex: Using AGENTS.md to describe the environment the sandbox must respect
- ChatGPT Codex: Scoping tasks tightly enough that the agent can finish in one pass
- ChatGPT Codex: Letting Codex open the PR while you stay the reviewer of record
- ChatGPT Codex: Pairing Codex with tight acceptance criteria for the first time
- ChatGPT Codex: Measuring what Codex actually merged, not what it attempted
- ChatGPT Codex: Small playbook that made Codex predictable
- ChatGPT Codex: Choosing Codex for upgrades, humans for design
- ChatGPT Codex: First time we stopped Codex mid-task and why
- ChatGPT Codex: Budgeting Codex tasks when usage was still a black box
- ChatGPT Codex: Diff-first review habit we learned from Codex
- ChatGPT Codex: When Codex rewrote code we did not ask it to
- ChatGPT Codex: Scoping tasks to finish in a single pass, a beginner lesson
- ChatGPT Codex: First Codex PR that shipped without a human touch
- ChatGPT Codex: Parallel tasks and the temptation to scope too wide
- ChatGPT Codex: Sandbox surprises in the first month of Codex
- ChatGPT Codex: Writing AGENTS.md for a team that had never used agents
- ChatGPT Codex: First Codex task that opened a real pull request
- ChatGPT Codex: Pairing Codex with tight acceptance criteria for the first time
- ChatGPT Codex: Measuring what Codex actually merged, not what it attempted
- ChatGPT Codex: Small playbook that made Codex predictable
- ChatGPT Codex: Choosing Codex for upgrades, humans for design
- ChatGPT Codex: First time we stopped Codex mid-task and why
- ChatGPT Codex: Budgeting Codex tasks when usage was still a black box
- ChatGPT Codex: Diff-first review habit we learned from Codex
- ChatGPT Codex: When Codex rewrote code we did not ask it to
- ChatGPT Codex: Scoping tasks to finish in a single pass, a beginner lesson
- ChatGPT Codex: First Codex PR that shipped without a human touch
- ChatGPT Codex: Parallel tasks and the temptation to scope too wide
- ChatGPT Codex: Sandbox surprises in the first month of Codex
- ChatGPT Codex: Writing AGENTS.md for a team that had never used agents
- ChatGPT Codex: First Codex task that opened a real pull request