HackerTrans
TopNewTrendsCommentsPastAskShowJobs

french_exec

no profile record

Submissions

[untitled]

1 points·by french_exec·الشهر الماضي·0 comments

[untitled]

1 points·by french_exec·قبل شهرين·0 comments

[untitled]

1 points·by french_exec·قبل 3 أشهر·0 comments

[untitled]

1 points·by french_exec·قبل 4 أشهر·0 comments

[untitled]

1 points·by french_exec·قبل 4 أشهر·0 comments

What a Null Result Taught Us About AI Agent Evaluation

clouatre.ca
1 points·by french_exec·قبل 5 أشهر·0 comments

Why Your AI Agent Failed in Production

clouatre.ca
1 points·by french_exec·قبل 5 أشهر·2 comments

Orchestrating AI Agents: A Subagent Architecture for Code

clouatre.ca
1 points·by french_exec·قبل 5 أشهر·0 comments

RAG for Legacy Systems: 7,432 Pages to 3s Answers

clouatre.ca
4 points·by french_exec·قبل 6 أشهر·0 comments

comments

french_exec
·قبل شهرين·discuss
"Unfortunately, GPT‑5.5 started training before we found the root cause of the goblins. When we began testing GPT‑5.5 in Codex, OpenAI employees immediately noticed the strange affinity for goblins, and we added a developer-prompt instruction (opens in a new window) to mitigate. Codex is, after all, quite nerdy."

https://openai.com/index/where-the-goblins-came-from/
french_exec
·قبل 5 أشهر·discuss
Fair point. Probabilistic systems being unpredictable isn't news. The article's just noting current observability tools weren't designed for these failure modes.