List from buildsoftwarewithai.com
AI for Developers
Tools, techniques and ideas for building software with AI.
Latest podcasts
Newest first
Updates are delayed. Showing the last checked articles.
I Wrote a War Fought With AI Weapons. How Close Is Fiction to Reality?
AI is already changing warfare. Drawing on the ideas behind An Unlikely War, this article explores autonomous weapons, human control and what happens when military decisions begin moving at machine speed.Read All
The Joining Tax: A Year of Governing Claude Code
Multi-agent coding setups lose context at every handoff not because the design is broken, but because the boundary is the whole reason those roles exist and the handoff is its price. To make the seam cheap, you need capped review rounds, a priority order per role, structured handoffs, one owner for the issue list, and a doc-updater that closes the loop.Read All
DHH's Vibe Coding Advice Ignores the Biggest Problem With AI-Generated Code
DHH advocates vibe coding without review, but is there enough evidence to trust AI-generated software over the long term?
Neuromorphic Vision vs. Traditional Still-Frame Cameras: Which One Wins the Surveillance Race?
Most video surveillance still runs on traditional still-frame cameras that capture full frames at a fixed rate. Neuromorphic (event) cameras work differently: each pixel fires only when its brightness changes, mimicking the human retina and outputting a sparse stream of events instead of frames. Independently reported specs back the advantages including ~120–140 dB dynamic range vs. ~60 dB, microsecond latency, chip-level power in the tens of milliwatts, and effectively no motion blur.
Tunnl Partners With DeepIntent to Reach Healthcare Audiences with Research-Backed Precision
Tunnl, an AI-powered audience intelligence platform, partnered with DeepIntent, a leading healthcare marketing platform, to provide research-backed audience segments to healthcare marketers. This integration brings new dimensions to campaign planning, enabling marketers to understand attitudes, behaviors, and motivations that shape healthcare decisions.Read All
HireQuotient Announces an Integration with BambooHR to Bring AI-Native Recruiting to Key Industries
HireQuotient, a leading AI-native recruitment technology company, has integrated its EasySource platform with BambooHR's Applicant Tracking System (ATS) to empower organizations with hyper-specialized hiring tools. The integration supports HR teams managing large applicant volumes and offers a cost-effective way to pair BambooHR's HR platform with additional recruiting capabilities.Read All
Anvil Announces SDK Launch, Enterprise Partnerships, and $5M ANVL Token Sale
Anvil, a decentralized finance protocol, is gaining traction among businesses and institutional investors, with companies like Bullish and investors led by Founders Fund working with the protocol to explore its applications. The protocol's universal collateral layer allows digital assets to secure verifiable financial commitments, making it practical for businesses to integrate into their products and services.Read All
Building resilient systems with Sam Newman
Sam Newman joins me to discuss when to use microservices, how to build resilient distributed systems, and how AI is changing software development.
Can AI Keep Growing Exponentially? Let’s Ask SemiAnalysis — With Dylan Patel and Jordan Nanos
Dylan Patel is founder and CEO of SemiAnalysis, Jordan Nanos is a member of its technical staff. Patel and Nanos join Big Technology to discuss whether AI’s massive infrastructure buildout can justify the trillions of dollars being spent on compute. Tune in to hear how big the boom could get, where the revenue needed to support it will come from, and what it could mean for knowledge work and the broader economy.
Switching Models Shouldn’t Mean Starting Over | Walrus Protocol’s Kimberly Logan
If your agent's memory lives inside one model provider, switching models or harnesses means starting over. You need portable memory - yet when switching agent memory between models, you can swing accuracy by thirteen points or more, depending on which model reads them back. This episode is sponsored by Walrus.
Your customers won’t ask for Gemini 4 Argon. Their best AI product idea probably isn’t in their feature requests either. Four questions surface the work they gave up on
Google’s new Gemini 4 Argon model has impressive benchmark results. Google says it leads the Vals Index, which evaluates professional work across several fields. The initial rollout is limited to trusted cybersecurity defenders, with broader access planned. Google has described internal uses and early customer work, but most of us still can’t use it ourselves.
ComplexMCP Finds Tool-State Gaps
ComplexMCP is a useful benchmark because it tests the part of tool use that simple function-calling tasks avoid: one action changes the state that the
What FDEs Own After the AI Demo Works
From customer discovery to production readiness: lessons from my FDE Talks conversation with Akshay, a forward deployed engineer on Salesforce’s Agentforce team.
Infrastructure Listed Giant Mattr Selects HireQuotient’s EasySource to Transform Talent Acquisition
HireQuotient, an enterprise AI technology company, announced that Mattr, a global leader in advanced materials technologies, has selected its flagship platform, EasySource, to streamline its hiring operations. This partnership underscores a broader trend of leading manufacturing organizations trusting HireQuotient's AI-native solutions to combat recruiter fatigue and engage specialized candidates at scale.Read All
Make Product Marketing Human Again: Keeping it Authentic in the Age of aI
AI makes marketing faster, but does it make brands forgettable? Discover why human creativity, storytelling, and original thinking still matter.Read All
A Beginner's Guide to Writing AGENTS.md Files for Codex
Learn what belongs in global and project AGENTS.md files, with practical examples, override rules, and ways to check what Codex loads.Read All
The Hidden Language Tax Making AI More Expensive for Non-English Users
Claude Opus 5 uses nearly 3x more tokens for Russian than English. Here's why AI tokenization makes some languages more expensive than others.Read All
I Passed the AWS AI Business Strategist (AIB-C01) Beta With Claude and Notion: Here's How
I passed the AWS Certified AI Business Strategist (AIB-C01) beta on the first day it was available, with no third-party prep material out at announcement. The setup: a Claude project running my study instructions, connected to a Notion hub of notes, rules, a quiz database and a Fact Sheet. Do Claude drills first to find what you already know, log every practice-test miss in Notion, and build a Fact Sheet, because the exam had more straight definition questions than expected.Read All
How to Evaluate RAG Systems When Ground Truth Keeps Changing
Summary In this episode Ofer Mendelevitch shares what it really takes to evaluate RAG systems in production when your source data is incomplete, constantly changing, or difficult to validate against a clean ground truth. He explores how RAG has evolved from simple “chat with your PDF” demos into enterprise-grade retrieval systems that require robust ingestion pipelines, hybrid search, reranking, multimodal support, access controls, and refresh strategies for large and dynamic document collections.
Gemini 4 Argon: How Does It Do Against GPT-6 Astra and Claude?
Google DeepMind has announced Gemini 4 Argon, a frontier model that excels in long software engineering jobs, legal and finance work, and cyber defense, outperforming GPT-6 Astra and other models in various benchmarks. Argon can write up to 1M output tokens in a single response and is currently available to trusted cyber defenders through Google's Fairwind Program, with aRead All
Showing 20 of 200 podcasts
Know a source we’re missing? Tell us about it