TL;DR: āSelf-consistencyā, ask a model the same question several times at a non-zero temperature and take the answer they most agree on (a plurality vote), gives large accuracy gains over greedy decodā¦
AmazonBedrock
28 posts tagged AmazonBedrock Ā· all tags
2026
Self-Consistency Is Just Probability Amplification
Generate-and-Verify: What P vs NP Teaches Us About AI Reasoning
TL;DR: The defining feature of the complexity class NP is polynomial-time verifiability: a candidate answer is cheap to check. The asymmetry that matters shows up in its hardest members, the NP-compleā¦
Stop Guessing Which Coding Agent to Use ā Benchmark It on Your Own Tasks
TL;DR: Generic coding-agent leaderboards donāt tell you which model or tool fits your work at a budget youāre willing to spend. So I built a small task set that mirrors my real work and ran an open-soā¦
The Quadratic Wall: The Algorithmic Race to Beat O(nĀ²) Attention
TL;DR: Standard self-attention costs on the order of nĀ² in the sequence length n, in both arithmetic and the attention-score memory it materialises. Almost every long-context architecture headline of ā¦
From Robot Soccer to the Agentic World Cup: Why Games Move AI Forward
š¬ Also available as a blog walkthrough video: a narrated screencast of this post. TL;DR: Twenty years ago, a year-long university project group I was part of built a team of soccer-playing cube robotsā¦
Why AI Tokens Are So Expensive ā and What Actually Makes Them Cheaper
TL;DR: Autoregressive LLM generation has two phases with different bottlenecks: prefill processes input positions in parallel and is usually compute-intensive, while decode produces tokens sequentiallā¦
Vector Search, From the Whiteboard to the Cloud
š¬ Also available as a blog walkthrough video: a narrated screencast of this post. TL;DR: Vector search is easy to picture on a whiteboard: turn text into a list of numbers, then find the stored items ā¦
Agent Memory Is a Spectrum, Not a Switch
š¬ Also available as a blog walkthrough video: a narrated screencast of this post. TL;DR: āMy agent keeps forgetting thingsā is usually not a model problem. Itās a memory-architecture problem. Agent meā¦
I Rebuilt a Browser Fact-Checker on AWS, and AgentCore Web Search Was the Missing Piece
š¬ Also available as a blog walkthrough video if youād rather watch than read. TL;DR: I came across an open-source browser extension that fact-checks videos and live streams in real time, and I wanted ā¦
Give Every Agent Its Own Computer: AWS Lambda MicroVMs
š¬ Also available as a blog walkthrough video where I walk through the post and the demo. TL;DR: AWS Lambda MicroVMs (launched 22 June 2026) gives every user, job, or AI agent its own isolated, statefuā¦
Getting Paid by Agents: A Managed Paywall at the Edge
š¬ Also available as a blog walkthrough video with a narrated tour of the build. TL;DR: In Part 2 I built the buy side: an agent that autonomously pays per article over x402 with Amazon Bedrock AgentCoā¦
Your Voice Clone Is Only as Good as the Reference Clip
š¬ Also available as a blog walkthrough video with narrated diagrams. TL;DR: A voice clone built by conditioning on a reference clip, Qwen3-TTS, in my case, inherits the clipās cadence, pitch, and timbā¦
MCP Strategies on AWS, Part 2: Tool Design in Code
TL;DR: The AWS Prescriptive Guidance paper on MCP gives the most useful, checkable rules in its tool-design section, so I wrote code to test them. A token-tax counter on a realistic 20-tool GitHub serā¦
MCP Strategies on AWS, Part 1: Reading the Whole Guide
š¬ Also available as a blog walkthrough video with narrated diagrams. TL;DR: AWS published a Prescriptive Guidance paper, āModel Context Protocol strategies on AWS,ā that organizes MCP into three pillaā¦
Claude Fable 5 on Bedrock: A Hands-On Comparison, and the Data-Retention Switch You Set First
TL;DR: Claude Fable 5 went GA on Amazon Bedrock yesterday (June 9, 2026), so within a day I ran it head-to-head against Opus 4.8 and Sonnet 4.6 (all three invoked from Frankfurt through EU Geo inferenā¦
Why Your Cheapest Model Should Write the Harness
TL;DR: A May 2026 paper separates two capabilities that self-improving agents usually conflate: writing harness updates and benefiting from them. Writing is flat across model tiers: a 9B open model prā¦
I Built the Agent That Pays ā Here's What I Learned
TL;DR: A couple of weeks ago I wrote about HTTP 402 and why AI agents might finally activate the internetās oldest unused status code. The post sparked a real discussion, so I built it: a research ageā¦
Welcome to the Family: I Sat GPT-5.5 and Claude Opus Down on Bedrock
TL;DR: OpenAIās GPT-5.5, GPT-5.4, and Codex went GA on Amazon Bedrock on June 1, 2026. To get a feel for it, I wired up two Strands agents, Claude Opus 4.8 and GPT-5.5, and let them chat, with Opus plā¦
The Service Catalog Pattern for AI Agents
TL;DR: AI agents face the same discovery problem microservices solved with service registries a decade ago, except agents need semantic search, governance workflows, and dynamic capability updates. AWā¦
Your AI Judge Needs a Judge
TL;DR: Most teams I see ship LLM judges without testing them against human labels. The result: judges that are confidently, consistently wrong on 30%+ of cases. Hamel Husainās ācritique shadowingā metā¦
8 AWS Guides for Agentic AI ā Mapped to the 4 Pillars That Get You to Production
The Gap Between Demo and Deployment TL;DR: AWS released 8 prescriptive guides for building production-ready agentic AI. This post maps each guide to the four pillars that get agents from demo to deploā¦
Intelligence Is About Time, Not Parameters
The Question Every SA Gets Beyond a complexity threshold, larger models become less insightful, the savant regime. āWhich model should I use?ā I hear it in almost every customer conversation about genā¦
Hackathon Gamification: A Real-Time Leaderboard You Can Deploy in 5 Minutes
Lisbon, 6 AM, Rising Sun Lisbon at dawn, the best way to start a hackathon day Three days in Lisbon. Not for sightseeing, though the city makes that hard to resist. Iām here for an AI hackathon, teamsā¦
The Agent Security Stack Nobody Is Building
The Scenario Nobody Planned For Itās 11 PM. Your customer support agent, the AI one, is processing a refund request. It queries the order database, pulls the customerās payment history, and calls the ā¦
Building Agents That Read the Web Right
The Other Side of the Coin In a recent article, I made my website AI-agent friendly [1], adding llms.txt, Markdown output, and content negotiation to a Hugo site on AWS. That article was about the proā¦
Is RAG Still Needed with 1M+ Token Context Windows?
The Kofferklausur, Revisited In September 2024, a colleague asked an audience: āWhat is RAG?ā I answered: Kofferklausur [1]. For non-German speakers: a Kofferklausur is an open-book exam. You bring yoā¦
When Thinking Twice Helps ā And When It Doesn't
The Saturday Morning Experiment Last Saturday, I installed a Python library, pointed it at Amazon Bedrock, and asked a model the same questions three times, with zero, one, and three rounds of self-reā¦
Your AI Models Have an Expiry Date ā A Practical Guide to Model Lifecycle Management
Introduction, The Promise I Made In my previous article [1], I explored the maintenance trap in IT, how software systems are more like plants than stones, requiring constant care. I ended with a cliffā¦