Problemsby IbisOpenAI gives confidently wrong answers
LLM apps2 posts from 2 people2d active+00 posts in the last 7 days, 1 the 7 days before (fading)Unverified
Posts per day
The posts behind it
2, newest first...assigns fp_probability (LOW/MEDIUM/HIGH) - confident cases skip the debate entirely, so expensive LLM calls fire only on genuinely ambiguous findings.. There's a BYO-LLM invariant underneath all of this: GSC never depends on its own model key. You bring your own (DeepSeek,...#python on Mastodon · @hackaday@www.urbanmind.net1 likes and boostsOpen ↗_handle_invalid_parallel_tool_calls shift off-by-one leaves leftover multi_tool_use.parallel## Description `_handle_invalid_parallel_tool_calls` expands hallucinated OpenAI `multi_tool_use.parallel` tool calls, but its splice `shift` is off-by-one. When **two or more** such calls appear in one assistant message, expanding the first leaves the second original...BerriAI/litellm · michaelkillgta1 repliesOpen ↗
Companies and products named
About this problem
Evidence
2 posts from 2 people in 2 places, about 1 a week over 14 days. Mostly on BerriAI/litellm, #python on Mastodon. Tools named alongside: DeepSeek, Ollama, OpenRouter.
Frustration Frustration 3 of 3· Seen on GitHub issues, Mastodon
How it was grouped
Posts that state a pain and match the "hallucination" rule about OpenAI. First post Sep 25, 2026, latest Oct 8, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
The same problem elsewhere
LLMs give confidently wrong answersGemini gives confidently wrong answersClaude gives confidently wrong answersGitHub Copilot gives confidently wrong answersOllama gives confidently wrong answersGitHub gives confidently wrong answersGrok gives confidently wrong answersChatGPT gives confidently wrong answersModel Context Protocol gives confidently wrong answersClaude Code gives confidently wrong answers
Other OpenAI problems
Fine-tuning OpenAI is costly and unpredictableOpenAI users keep asking for helpRunning OpenAI locally hits memory and speed limitsOpenAI upgrades break working setupsTrouble with OpenAI chatTrouble with OpenAI responsesOpenAI fails to return valid structured outputTrouble with OpenAI astraTrouble with OpenAI customTrouble with OpenAI imageOpenAI tables suffer from small files and skewTrouble with OpenAI crashes
History
steady to fading
OpenAI gives confidently wrong answers (2 posts)