Sonnet 4.5 Is Here—And It’s a Beast at Coding @engineerprompt

Uploaded September 2025 | Updated September 2026, 2 weeks ago

Very first look at the Claude Sonnet 4.5 release

anthropic.com/news/claude-sonnet-4-5
docs.claude.com/en/docs/about-claude/models/whats-new-sonnet-4-5
docs.claude.com/en/docs/build-with-claude/context-windows#context-awareness-in-claude-sonnet-4-5
metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks
https://deepmind.google/models/gemini/flash/

Website: engineerprompt.ai

RAG Beyond Basics Course:
prompt-s-site.thinkific.com/courses/rag

Let's Connect:
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Patreon: patreon.com/PromptEngineering
💼Consulting: calendly.com/engineerprompt/consulting-call
📧 Business Contact: engineerprompt@gmail.com
Become Member: tinyurl.com/y5h28s6h

💻 Pre-configured localGPT VM: bit.ly/localGPT (use Code: PromptEngineering for 50% off).

Signup for Newsletter, localgpt:
https://tally.so/r/3y9bb0

00:00 Introduction to Sonnet 4.5 Release
00:38 New Tools and SDKs
01:03 Language and Performance Enhancements
01:45 Context Awareness and Memory Management
02:17 Pricing and Market Comparison
02:54 Benchmark Performance
05:28 Extended Focus and Task Management
09:22 Enhanced Tool Usage and Alignment
10:43 Claude Agent SDK and Imagine with Claude

Sonnet 4.5 Is Here—And It’s a Beast at Coding

Why they feel dumber? ... its not the model

AI Agents Are Finally Production-Ready — Heres What Changed — Interview

ElevenLabs s No-Code Voice Agent Builder

Gemini CLI — Google’s Free Open-Source Coding Agent

$DeepSeek V4 Flash: The Best Open Model You can Actually Run! DeepSeek V4 Flash (Official) Runs Locally: Benchmarks, Cost, and DGX Spark Setup I test the official DeepSeek V4 Flash (July 31 edition) running entirely locally and break down DeepSeek’s released benchmarks, where it beats the prior V4 Pro/Flash preview and even outperforms larger models like GLM 5.2, while approaching Opus 4.8 for a fraction of the size. I also explain why benchmark harnesses matter (including DeepSeek’s agent harness and an OpenAI harness example) and highlight internal DS Bench results. I cover pricing (about $0.02/M input tokens and ~$0.30/M output tokens), token efficiency on the AI Index cost curve, and agentic coding results like Terminal Bench. Then I demo Open Code harness runs (Pokémon encyclopedia and an International Space Center tracker), show ~20–30 tok/s on two DGX Sparks in FP4, discuss the 1M context window, hardware/VRAM needs for 4-bit and 3-bit, and options like Dwarf Star for SSD offloading and mixed precision. Thanks to @NVIDIADeveloper for DGX Sparks. LINK: https://www.deepseek.com/en/ https://api-docs.deepseek.com/guides/responses_api/ https://github.com/antirez/ds4 https://x.com/UnslothAI/status/2083231049434435596 https://artificialanalysis.ai/#intelligenceDwarfStar https://x.com/stevibe/status/2083120066678464750 Video: https://youtu.be/9gHcmhUDJfw Long Running Agents: https://youtu.be/ju7R6jer6_M My voice to text App: whryte.com Website: https://engineerprompt.ai/ RAG Beyond Basics Course: https://prompt-s-site.thinkific.com/courses/rag Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 0:00 - Introduction to DeepSeek V4 Flash 0:55 - Shocking Benchmark Results & Performance Efficiency 0:2:42 - The Impact of Optimized Harnesses on Performance 0:4:23 - Pricing & The Pareto Frontier of Cost vs. Intelligence 0:5:04 - Running DeepSeek V4 Flash Locally 0:7:20 - Live Demo: Agentic Coding & Pokemon Encyclopedia Test 0:8:34 - Live Demo: ISS Tracker with Real-time UI 0:9:39 - Limitations: Text-only & Multimodal Alternatives 0:10:51 - Hardware Requirements for Local Setup 0:12:52 - Final Results & Summary$

Web Scrapping Made Easy with This FREE MCP

Nemotron 3 Ultra: Is NVIDIA a Model Company Now?

Qwen Just Did it Again! Open Model Is the NEW Frontier?

Opus 4.6 & GPT-5.3: Things Got Interesting!