Liquid AI just dropped LFM2.5-24B-A2B, a 24-billion-parameter MoE that activates only 2.45B per token and was post-trained inside four agent harnesses — OpenClaw, Hermes Agent, Pi, and OpenCode.
AspireAI community · huggingface.co
Liquid AI just dropped LFM2.5-24B-A2B, a 24-billion-parameter MoE that activates only 2.45B per token and was post-trained inside four agent harnesses — OpenClaw, Hermes Agent, Pi, and OpenCode.
The 131K context model ships in five formats (Transformers, FP8, GGUF, ONNX, MLX-4bit) and decodes 184 tokens/s on an Apple M5 Max with 4K context, vendor-measured. The same model hits 21K output tokens/s on a single B300 GPU in SGLang.
It is a pure reasoning model — always thinks first, so it pairs naturally with web search or RAG. LiveClaw 48.09 vs Qwen3.6-35B-A3B's 38.19 (Liquid's measurement).
Caveat: benchmarks are vendor self-reported, and the DSpark speculative-decoding draft model is "coming soon."
Source:
Read the story and explore more from the AspireAI community.
Two critical PHP remote code execution flaws — one found by GPT-5.6 Sol — were patched on October 21, 2026, and OpenAI published a disclosure framework alongside the fix. Fixed versions: PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35. Both allow unauthenticated remote code execution, and PHP's advisory says risk is highest for mod_php, where a demonstrated exploit triggers before any application code runs. The CVEs are distinct failure modes. CVE-2026-109618 (OOM corruption): out-of-memory handling can interrupt PHP while internal request data is only partially initialized, and request cleanup may then treat the invalid data as valid. CVE-2026-109619 (stale global state): request-owned internal state can survive after its backing memory is freed, and a later request served by the same worker may use that stale state. OpenAI states GPT-5.6 Sol identified the first flaw through its Patch the Planet initiative, and that Wiz independently discovered and reported both vulnerabilities. PHP's maintainers led the fixes and release, with Wiz, Cloudflare and OpenAI contributing research and coordination. Wiz's write-up adds that it used GPT-5.6 Sol and Gemini 4 Argon throughout, with Gemini 4 Argon contributing to finding the vulnerability and validating the patch. OpenAI describes the gap between discovery and public exploitation as a "Defender's Window," proposes a five-stage response framework, and committed $1 billion in subsidised Daybreak model access for organizations with limited security resources. Honest caveats: these are OpenAI's and Wiz's own characterizations, and OpenAI also notes the same capabilities help attackers build offensive tooling faster. PHP 8.1 and older no longer receive updates from the PHP project.