#LLM

Compresr's YC-backed Context Gateway is a proxy between AI agents and LLM APIs. Its three pillars - preemptive summarization, tool output compression, and tool discovery - reduce wasted context-window usage.

Sakura Internet's "Sakura AI Engine" is an LLM inference platform compatible with OpenAI API. There is a free limit of 3,000 requests per month, and multiple models such as Kimi-K2.5 and gpt-oss-120b can be used domestically.

Cursor released Composer 2 without disclosing its base model; calling its OpenAI-compatible API revealed it is Kimi K2.5. This escalated into a licensing dispute, but a formal commercial agreement with Moonshot AI was subsequently confirmed.

AttnRes to replace Transformer's fixed residual combination with softmax attention in the depth direction. Demonstration with Kimi Linear 48B improved GPQA-Diamond +7.5pt and HumanEval +3.1pt. Training overhead was kept below 4% and inference below 2%.

A CVSS 9.3 unauthenticated RCE in LangFlow was confirmed in real-world attacks within 20 hours of public disclosure.

H Company's Holotron-12B uses a memory-efficient new design to lift PC-operation AI throughput to 8,900 tokens per second. Unsloth has released the beta of 'Studio,' a browser tool for no-code model fine-tuning.

Two long-standing reference publishers sued OpenAI, alleging that roughly 100,000 articles were used without permission to train LLMs.

AI Security for Apps reached GA, letting Cloudflare block prompt injection and PII leaks at the WAF layer. On the same day, it also launched RFC 9457-compatible error responses that replace HTML with JSON or Markdown when AI agents hit Cloudflare errors.

Anthropic has GA’d a 1M‑token context window. No surcharge for long context; image/PDF per‑request limit raised from 100 to 600. Achieved a frontier‑model best score on MRCR v2.

HuggingFace conducts a comparative analysis of 16 open source RL training libraries based on 7 design axes. In the synchronous type, the GPU utilization remains at around 60% due to the generation bottleneck, but with an asynchronous separation design it can be improved to over 95%.

Sarvam AI released 30B and 105B models trained entirely in India—from pretraining through RL—featuring support for 22 constitutionally recognized Indian languages and inference optimizations.

Andrej Karpathy released Autoresearch, a system where an AI agent autonomously runs machine-learning experiments on a GPU and tries 100 variants overnight. The article breaks down the mechanism and design so even readers with zero ML background can follow.