AI coding and developer tools news. GitHub Copilot, Claude Code, Cursor updates. Model coding benchmarks and capabilities.
Get our weekly newsletter on pricing changes, new releases, and tools.
November 20 2026 —
Self-hosting LLMs on GPUs means paying to recompute the same context on every turn. Distributed KV caching with Amazon ElastiCache can cut inference cost by up to 40% and time to first token by up to 80%. This post walks through the distributed KV caching skill in the Agent Toolkit for AWS, which evaluates and sets up the cache from your coding agent.
Proving software correct with math has traditionally required specialist work. Now AI and Lean are helping automate the process.
A new report from the AI evaluation nonprofit METR finds that some AI capabilities are continuing to improve along an exponential trajectory—but it also indicates that models aren’t quite as good at tasks that require judgment as they are at coding. The report is an update to the organization’s time horizon plot, which was widely…
Kimi Code CLI v2.7.0 adds a native Amazon Bedrock provider, so you can connect the open source coding agent to models like Kimi K3.1 Pro using your standard AWS credential chain (named profiles or SSO) instead of a separate API key. This post shows how to configure the provider and send your first request.
If you checked your bank balance, booked a flight or ordered groceries online today, there is a good chance your request was handled by a computer program written in Java.
November 18, 2026 — Google’s middle tier scores 61 on the Intelligence Index. Plus, Anthropic prices its IPO at $83.
Amazon SageMaker AI Serverless Model Customization now supports Full Fine-Tuning (FFT). This post explores when FFT outperforms LoRA across key benchmarks, examines the spectral properties of model weight matrices behind the quality gap, shares practical hyperparameter tuning guidelines, and shows how to get started.
Airbnb runs evals on real engineering tasks and uses Amazon Bedrock observability to choose models for its coding agents and control production costs. This post shows how cost per task guides model selection, why production spending can differ from eval results, and how to monitor latency, manage quotas, and attribute spend.
Just three years after launching with zero revenue, Anthropic brought in $17 billion and says more than 11,900 customers now spend at least $100,000 a year. But its IPO filing also reveals enormous computing commitments and big questions about balancing growth with risks.
Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work. It is suited for repository and terminal coding, web...
November 17, 2026 — GPT-6.2 Astra and Sol lower benchmark costs. Early testers disagree on what Astra is like to work with.
OpenAI measures how coding agents are accelerating AI research, where their performance remains uneven, and what this signals about recursive self-improvement.
The biggest cost lever in a generative AI system is whether you call a model at all. Learn how to decide whether each workflow step needs a model, and map each option to AWS: deterministic code, a constrained decision call, or a right-sized model on Amazon Bedrock.
SMART, an open-source Python SDK and Terraform stack, deploys the full WhatsApp channel layer to your AWS account with one command. Bring any agent that runs on Amazon Bedrock AgentCore, and SMART handles webhook ingestion, media, conversation memory, scheduling, and Meta message templates.
Discover how continuous improvement in Microsoft Foundry helps organizations evaluate, optimize, and improve agents over time while keeping teams in control. The post Continuous improvement comes to Microsoft Foundry appeared first on Microsoft Azure Blog .
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
2026 68 Ventures, LLC. All rights reserved.