onllm.dev
Insights on AI development, privacy-first solutions, and building intelligent applications.
6 posts updated Nov 2026TypeSafe AI exited stealth with $40M and Jev, a model that returns typed decisions with probabilities it calls calibrated, backed so far only by the company's own benchmark.
Anthropic releases Claude Sonnet 4.6 with 1M token context window, record SWE-Bench scores, and unchanged pricing at $3/$15 per million tokens.
ReadAnthropic's Opus 4.6 brings a 1M token context window, parallel agent teams, and adaptive thinking but OpenAI's GPT-5.3-Codex landed 27 minutes later.
ReadFinance Minister Nirmala Sitharaman mentioned AI 11 times in her Budget 2026-27 speech — the highest count ever. But beyond rhetoric, the infrastructure commitments signal someth...
ReadXiaomi and Moonshot AI release frontier-class open models that rival Claude and GPT-5 at a fraction of the cost. The future of AI is open, self-hostable, and no longer controlled by Silicon Valley.
ReadDeepSeek-OCR compresses text into visual tokens, achieving 10-20x efficiency gains. More than OCR — it's a new way to think about LLM context.
ReadBuilt by onllm.dev
Real tools solving real problems. Privacy-first, production-ready.
LiveAI life manager with 46+ trackers, WhatsApp integration & smart reminders.
Visit site
LiveSmart business card scanner. Digitize contacts instantly as a PWA.
Visit site
LivePractice management for CAs & CSs. Compliance, invoicing, one dashboard.
Visit site
BetaOn-device AI assistant for Android. Runs LLMs locally, zero data leaves.
Learn more
BetaPrivacy AI browser with agentic capabilities. BYOK, browse with AI locally.
Learn more
BetaEmotional wellness with CBT guidance, encrypted journaling & crisis support.
Visit site