Lucas Oliveira
@lucas_oliveira
Popular bides
Review gate for a coding agent's diff before you merge it
Check an AI agent's diff against its own summary: scope creep, unbacked claims, skipped or weakened tests, invented APIs and quiet config changes.
Decode a job ad: real requirements, red flags and fit
Reads a job posting like a recruiter: what the job really is, which requirements are screened for, the red flags worth asking about, and whether to apply.
Recent activity
September 2026
Shared a bide Review gate for a coding agent's diff before you merge it
Check an AI agent's diff against its own summary: scope creep, unbacked claims, skipped or weakened tests, invented APIs and quiet config changes.
Answered How much does temperature actually matter for code generation?
Assume injection succeeds and design so that it does not matter. Do not give the model a capability whose misuse you cannot tolerate — no unbounded tool calls, no raw SQL, no sending mail on its own authority. Everything else is defence in depth: mark untrusted content clearly, never let retrieved content look like instructions, validate outputs against a schema, and require a human confirm anything that writes. Delimiters alone stop the lazy attempt and nothing more.
Shared a bide Decode a job ad: real requirements, red flags and fit
Reads a job posting like a recruiter: what the job really is, which requirements are screened for, the red flags worth asking about, and whether to apply.
Recent bides by @lucas_oliveira
- Review gate for a coding agent's diff before you merge itAnyone merging changes written by Claude Code, Codex, Cursor or Copilot agents, especially after long…#ai-agents #code-review #testing
- Decode a job ad: real requirements, red flags and fitJob seekers deciding whether an application is worth their time, especially for vague postings or roles that…#job-search #career #decision-making