Tag
BotsCrew reports benchmark results comparing GPT-5.6 Luna to GPT-5.2 ahead of OpenAI's January 14 shutdown of GPT-4o and GPT-4.1, finding the cheaper Luna models win on cost but perform worse on long tool-heavy conversations and guardrails.
一条带有讽刺意味的帖子称ChatGPT网页版已彻底移除GPT-5.5支持,即使GPT-6已发布,许多用户仍坚持使用GPT-5.5,官方以「听取用户声音」为由直接剥夺用户选择权。原文:A satirical post claiming GPT-5.5 support has been completely removed from the ChatGPT web version, mocking how users' choice was revoked despite many still preferring GPT-5.5 over GPT-6.
Google has sunsetted Gemini 3.7 Flash only two months after its release, marking a notably short lifespan for the model.
Google announced changes to how developers and users access its Gemini models starting October 9, potentially affecting API quotas, available model versions, or access tiers.
The tweet announces the upcoming retirement of the AI model GPT-5.3-Codex-Spark, citing declining usage and the availability of better models, reflecting advancements in AI development.
A tweet mourning the impending removal of GPT-4.5, encouraging users to experience its creative writing capabilities before it's gone.
A discussion of common errors when calling LLM APIs in production, including rate limits, format mismatches, malformed responses, context overflow, model deprecation, and silent failures, with statistics from Datadog and a cited paper.
Claude Fable 5 will be taken offline in a few weeks, with details on the reasons for its removal.
OpenAI announced GPT-4 API general availability and deprecated older completion models (GPT-3 base models and text-davinci-003), requiring developers to migrate to new models like gpt-3.5-turbo-instruct or newer by January 4, 2024. Fine-tuned models will need to be retrained on new base models with priority access offered for GPT-3.5 Turbo and GPT-4 fine-tuning.