Tag

#llm

44 posts

LLM & IntegrationJuly 8, 202617 min
Semantic Cache for LLM Calls with Redis Vector Sets (2026)
Build a semantic cache for LLM calls with Redis 8's native VADD/VSIM vector sets in Node.js and TypeScript — cache hits on paraphrases, not just exact text.
NewsJuly 2, 202613 min
Claude Fable 5 Returns After Export Ban Lifted (2026)
Claude Fable 5 is back after the US lifted export controls tied to an Amazon-reported jailbreak. Here's the full timeline and what changed for API users.
NewsJuly 1, 202610 min
Claude Sonnet 5: Cheaper Agents, Near-Opus Power (2026)
Claude Sonnet 5 brings near-Opus 4.8 agentic coding at $2/$10 per million tokens through August. See the pricing, the tokenizer catch, and the system card.
NewsJune 29, 202612 min
GPT-5.6 Sol: OpenAI's Government-Gated Preview (2026)
OpenAI previewed GPT-5.6 Sol, Terra, and Luna on June 26, 2026 — but only to government-vetted partners, via API and Codex, under the cyber EO 14409.
Security & PrivacyJune 28, 202611 min
AI Coding Governance Gap: 97% Adoption, 30% Control (2026)
AI coding tools hit 97% enterprise adoption in 2026, but only 30% of teams fully govern them. Inside the AI coding governance gap, its risks, and the fix.
LLM & IntegrationJune 28, 202616 min
Token-Aware Text Chunking for RAG in TypeScript (2026)
Token-aware text chunking for RAG in TypeScript: recursive splitting with @langchain/textsplitters and js-tiktoken, plus chunk size and overlap tuning.
AI & Machine LearningJune 23, 20268 min
GLM-5.2: Open-Weight 1M-Context Coding Model (2026)
Z.ai's GLM-5.2 is a 753B-parameter, MIT-licensed open-weight model with a usable 1M-token context. See its coding benchmarks, pricing, and how to run it.
AI & Machine LearningJune 15, 202613 min
Claude Prompt Caching in TypeScript: Cut Costs 2026
Add Claude prompt caching in TypeScript with cache_control: measure cache_read_input_tokens, cut API costs ~89%, and avoid the silent minimum-token cache miss.
AI & Machine LearningJune 11, 202620 min
Claude Batch API in TypeScript: Bulk Extraction (2026)
Claude Batch API tutorial in TypeScript: submit thousands of structured-output requests at 50% cost, poll status, stream results, and validate with Zod.
AI & Machine LearningJune 7, 202619 min
Claude Structured Outputs in TypeScript with Zod (2026)
Get guaranteed JSON from the Claude API in TypeScript: structured outputs with Zod, strict tool use, plus refusal and max_tokens handling. Runnable 2026 guide.
AI & Machine LearningMay 29, 202615 min
Claude Tool Use in TypeScript: Agentic Loop Tutorial (2026)
Hands-on Claude Sonnet 4.6 tool use tutorial: build a typed agentic loop in TypeScript with the Anthropic SDK 0.98, parallel tool calls, and JSON Schema.
AI & Machine LearningMay 6, 202612 min
GPT-5.5 Instant: ChatGPT's New Default Model in 2026
OpenAI's GPT-5.5 Instant replaces GPT-5.3 as ChatGPT's default model on May 5, 2026, cutting hallucinations 52.5% on medicine, law, and finance prompts.

Every post in #llm (44)