Related reading
Claude Opus 5.5 now available on AI Gateway
Claude Opus 5.5 is now on Vercel AI Gateway, delivering ~30% speed and ~40% cost gains over Opus 5, a 1 M‑token context, and breaking API changes that require adaptive thinking and structured outputs. It can be accessed via Vercel’s SDKs, OpenAI‑compatible endpoint, and coding agents, with optional fast mode and regional/ZDR controls.
Vercelvercel.com2 minreleaseClaude Opus 5.5
Claude Opus 5.5 is Anthropic’s latest LLM, positioned to match Claude Fable 5.1 on most tasks while cutting compute cost by ~40% and latency by >30%. It ships with the same safety guardrails as the top‑tier models, scores best on Anthropic’s internal alignment audit, and shows measurable gains on coding‑heavy benchmarks (e.g., 66.4% on Agentic‑coding Terminal‑Bench vs 52.3% for Opus 5). Pricing d…
Hacker News front pageanthropic.com15 minreleaseHN17921117I’m Using GPUI For Everything
This post is a single sentence linking to a Syntax team video about why they are using GPUI for their projects. It provides no original content, summary, or details from the video itself.
Freek Van der Hertenfreek.dev1 minVideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents
Long-form video agents often suffer from 'semantic thrashing' where growing append-only memory causes attention collapse and loss of key evidence. VideoLoop proposes a two-loop memory management system that retrieves artifacts from a filesystem and rewrites a bounded working memory to mitigate this issue.
Hugging Face Daily Papersarxiv.org1 minpaper
