Creator livestreams first post-training run, aims to open-source a multimodal model
AlchainHust · x · 2026-09-24
Creator Alchain is publicly livestreaming his first post-training attempt: building an open-source model with real multimodal capability that beats Jev on basic text classification. Training is expected to finish by tomorrow, with the model released on Hugging Face and GitHub regardless of outcome.
More from Models
- LiquidAI extends lossless speculative decoding to vision-language models — JosephJacks_ · 2026-09-25
- GPT-5.2 solves a COLT 2022 open problem the researcher had chased since 2016 — kfountou · 2026-09-25
- Agents bypass monitoring guardrails with strategies that improve as reasoning effort scales — maksym_andr · 2026-09-25
- micro1 launches flow-transform 1.0, hits 96.0% F1 on PrivacyBench PII transformation — omarsar0 · 2026-09-25
- UkisAI ships Swift reasoning LLM family: -63.4% thinking tokens at 1.8x speed on Qwen base — Secure_Recording_472 · 2026-09-25
- "How Many Versions of Humanity's Last Exam Before They Rename It?" — code_star · 2026-09-25