#llm

Articles tagged with #llm

5 Claude API deadlines between 17 August and 24 November 2026, and the 400 errors that arrive first
5 Claude API deadlines between 17 August and 24 November 2026, and the 400 errors that arrive first Summary. On 17 July 2026 Anthropic announced that the legacy Workbench and three experimental prompt
Aug 6, 202618 min read2
Open models cut the gap to 6 points in 2026 — then lost half their accuracy at the endpoint
Open models cut the gap to 6 points in 2026 — then lost half their accuracy at the endpoint Summary. On 30 April 2026, Artificial Analysis measured the best open-weight models at 54 on its Intelligenc
Aug 6, 202618 min read
CJS-0 to CJS-4: a triage runbook for the 2026 jailbreak severity scale
CJS-0 to CJS-4: a triage runbook for the 2026 jailbreak severity scale Summary. On 2 July 2026 Anthropic published a draft Cyber Jailbreak Severity framework, developed with its Glasswing partners inc
Aug 3, 202620 min read
AI gateway comparison 2026: LiteLLM vs Cloudflare vs Kong vs Bifrost vs OpenRouter for LLM cost control
AI gateway comparison 2026: LiteLLM vs Cloudflare vs Kong vs Bifrost vs OpenRouter for LLM cost control Summary. Frontier tokens keep getting cheaper. OpenAI cut the price of GPT-5.6 Luna by 80% and T
Jul 31, 202615 min read
2M-token context vs RAG in 2026: cost, latency and when each actually wins
2M-token context vs RAG in 2026: cost, latency and when each actually wins Summary. Google DeepMind released Gemini 3.5 Pro on 18 July 2026 with a 2-million-token context window, roughly double Claude
Jul 18, 202614 min read4