You mean why it prints:
Batch size 256: …
not Batch size 2048: …
That's likely because the 2048 triggered the "except" due to exceeding the memory here.
It only prints the successful ones.
CODE
-
Memory Limit Exceeded: Batch Size 2048 Exception Handling
By
–
-
OpenAI Engineers Boost Codex Adoption to 92 Percent
By
–
92% of OpenAI engineers are using Codex – up from 50%. Nearly all PRs are reviewed now with Codex
-
Link to Flowise GitHub Repository
By
–
github.com/FlowiseAI/Flowise [Translated from EN to English]
→ View original post on X — @flowiseai, 2025-10-06 19:16 UTC
-
Flowise open source alternative to OpenAI AgentKit platform
By
–
Welcome to the game @OpenAI
— FlowiseAI (@FlowiseAI) 6 octobre 2025
btw, here's an open source version that support all models https://t.co/YhBCWXN3Tb pic.twitter.com/ssJ3C2sVsqWelcome to the game @OpenAI btw, here's an open source version that support all models OpenAI Developers (@OpenAIDevs) Introducing AgentKit—build, deploy, and optimize agentic workflows. 💬 ChatKit: Embeddable, customizable chat UI 👷 Agent Builder: WYSIWYG workflow creator 🛤️ Guardrails: Safety screening for inputs/outputs ⚖️ Evals: Datasets, trace grading, auto-prompt optimization — https://nitter.net/OpenAIDevs/status/1975269388195631492#m
→ View original post on X — @flowiseai, 2025-10-06 19:15 UTC
-
OpenAI Codex Hits 40 Trillion Tokens, Boosts Developer Productivity
By
–
Codex – 40t tokens for the gpt-5-codex model since launch, openai engineers do 70% more PRs with Codex (note, this is not amount of code written), and some new enterprise features. Sama promised big updates soon too
-
Visual builder API responses chat kit and evals for non-OpenAI models
By
–
Visual builder for responses API. Chat kit and a probably underrated one – evals for non openai models. Difficult for evals startups, not just agent startups
-
Anthropic Open-Sources AI Audit Tool for Claude Sonnet 4.5
By
–
Last week we released Claude Sonnet 4.5. As part of our alignment testing, we used a new tool to run automated audits for behaviors like sycophancy and deception. Now we’re open-sourcing the tool to run those audits.
