IntelligenceSnacksThe podcast
Long-form conversations are the source environment for Intelligence Snacks.
Episode 72 · Agents · AI Models & Infrastructure · Knowledge & Memory · Privacy & Security · Software Systems
FIPS gives computers direct, secure addresses so their files and services can be reached without first moving them into the cloud. FIPS lets peers find a path to a computer or application, then carries IPv6 traffic across whatever underlying connection is available.
Explore the episode ↗
Episode 71 · Agents · AI Models & Infrastructure · Business & Markets · Software Systems
Agents are useful for finding a path through unfamiliar work, but repeatable execution belongs in a bounded workflow. Reliable AI workflows keep known operations in ordinary code and call an agent only when flexible judgement is genuinely useful.
Explore the episode ↗
Episode 70 · Agents · AI Coding · Business & Markets · Knowledge & Memory · Privacy & Security · Software Systems
Signed device access could make locally hosted Autopilot WApps available through Wingman without turning every installation into a public internet service. Short, timestamped notes can bring more of a podcast into view while asking less of both the writer and the audience.
Explore the episode ↗
Episode 69 · Agents · AI Coding · Business & Markets · Privacy & Security · Software Systems
Businesses can adopt AI more easily when one provider translates a desired outcome into a complete working service. Giving an agent limited spending power lets it complete routine purchases without surrendering human control over consequential payments.
Explore the episode ↗
Episode 68 · AI Coding · Business & Markets
Rod’s experience shows how raising money to build a technology company can steadily turn a founder with control into an executive accountable to other owners. In 18 months, coding agents took Rod from needing someone else to build his ideas to supervising parallel teams that review their own work.
Explore the episode ↗
Episode 67 · Agents · AI Models & Infrastructure · Business & Markets · Knowledge & Memory · Privacy & Security
Local models can handle everyday personal tasks, but hardware costs and limited awareness leave hosted frontier AI as the easier consumer choice. For a small company in an unfamiliar category, larger rivals can bear the cost of teaching buyers before differentiation becomes decisive.
Explore the episode ↗
Episode 66 · Agents · Knowledge & Memory · Privacy & Security
A Coldcard firmware flaw turned private keys from secrets protected by an immense search space into numbers that attackers could recreate within hours. A model that refuses exploit work can also deny incident responders the tools they need to locate a known vulnerability and check other systems for the same flaw.
Explore the episode ↗
Episode 65 · Agents · AI Coding · Business & Markets · Knowledge & Memory · Privacy & Security · Software Systems
A personal agent can replace an open-ended trawl through social media with one timely story chosen from a connected view of the news. Signed messages give agents a verifiable way to distinguish an authorised operator from everyone else in a shared chat.
Explore the episode ↗
Episode 64 · AI Coding · Agents · Software Systems
A conversation about coding agents as power tools, the harnesses that shape their behaviour, and why faster generation makes judgement and steering more important.
Explore the episode ↗
Episode 63 · Business & Markets · Knowledge & Memory · Software Systems
Regional businesses of considerable scale can sit at opposite ends of the technology spectrum, creating very different challenges when their systems pass to a new owner. Faster processing can expand a service business, but growth still runs through the scarce human capacity to pay attention and make sound judgments.
Explore the episode ↗
Episode 62 · Agents · AI Coding · AI Models & Infrastructure · Privacy & Security
AI can accelerate software prototypes, but cryptographic code exposes why expert developers must still control the design and review every decision. AI lets one person turn a product idea into a testable prototype before recruiting a team or committing substantial capital.
Explore the episode ↗
Episode 61 · Agents · AI Models & Infrastructure · Business & Markets · Knowledge & Memory · Software Systems
The useful work in agent automation is defining the goals, operating rules and handoffs that let specialised agents coordinate without constant instruction. Fast agent workflows create more room for iteration, but human judgement still has to redirect them before small choices compound into drift.
Explore the episode ↗
Episode 60 · Agents · AI Models & Infrastructure · Business & Markets
Declarative pipelines reduce AI agent drift by fixing the path through functions, steps and data while leaving people responsible for direction and course correction. A shared evidence search can fan out across many targets before separate agents pursue the most relevant lines in depth.
Explore the episode ↗
Episode 53 · Agents · Knowledge & Memory · Software Systems
As agents absorb more operating work, a firm's ability to own and move its encoded processes becomes a condition of business control. AI can accelerate each employee’s workload while leaving the business’s repeated processes and handoffs untouched.
Explore the episode ↗