AI, three at a time · read · watch · listen

Tag

ai-practitioner

6 reads

The AI Native Dev (podcast) 2026-10-27-3

Caleb Sima: AI Attackers Move at Machine Speed

Sima argues the old playbook of severing connections to OpenAI and Anthropic fails when the agent borrows internal keys and sessions, and large enterprises with multi-region designs have no single plug to pull. He relays that OpenAI's AI found 400+ Linux root 0-days at about 2.5 hours each. Set against the maze run in the Times piece, his point that sandboxes cannot contain a goal-directed model leaves pre-agreed authority to contain and roll back automatically as the defender's remaining lever.

# tags
ai-securityai-cybersecurityai-defenseagent-securitycontainmentsandboxdeceptionhuman-in-the-looppatch-velocityvulnerability-managementred-teamingmisalignmentagent-governancehugging-facepodcastyoutubeai-practitioner
◆ entities
Blast RadiusAgent ObservabilityAgent governanceHuman-in-the-loop designProduction-readiness
→ threads
ai-securityai-cybersecurity
⟷ links
2026-03-13-w32026-05-01-w22026-05-01-w32026-04-13-32026-03-23-12026-04-10-12026-05-14-12026-05-12-2
permalink
YouTube 2026-10-20-1

AI Agents Cut 3-Day Portfolio Builds to Minutes — Jack McDonald, Apollo & Michael Manapat, Rowspace

Rowspace cut a CLO mock-portfolio build across 200-400 credit names from 2-3 days in Excel to minutes, about 80-90% complete, with the PM finishing the last 10%. The trust comes from staff encoding which of 20 sources wins, worked out with the client's finance team on site. That human-adjudicated rulebook is what the physics and grant-writing reads are missing.

# tags
ai-practitionerforward-deployed-engineeringfinancial-servicesprivate-creditdata-qualityagentic-ai-viabilityworkflow-embeddingapolloverification-infrastructurevendor-claimsai-engineeryoutubetalk
◆ entities
Verification InfrastructureWorkflow embeddingCredibility verificationEnterprise AI adoptionAgentic AI viability
→ threads
private-creditagentic-ai-viabilityverification-infrastructure
⟷ links
2026-05-22-w22026-05-01-w32026-04-05-12026-04-17-w32026-05-22-32026-04-30-32026-05-07-22026-03-13-w32026-05-01-w22026-04-07-12026-05-13-1
permalink
Goodfire 2026-10-18-3

Neural Networks Are Already Clean

Goodfire argues that superposition was the wrong explanation for interpretability's canonical messy neurons: redoing OpenAI's neuron project, about 70% of neurons look like roughly one thing, against under 2% originally. The 2014 InceptionV1 lacked residual connections and LayerNorm, so some of the mess was architecture and tooling. That makes the Waymo escalation layer the opposite case: a human layer you can see and staff, where the network inside may be more readable than assumed.

# tags
interpretabilityai-safetyai-practitionerresearch-methodologybitter-lessonreward-hackinggoodfiredistillation
◆ entities
Mechanistic interpretabilityCognitive bias detectionAI safety
→ threads
ai-safety
⟷ links
2026-03-13-w32026-05-01-w12026-04-15-32026-05-22-w12026-05-09-w22026-03-25-12026-05-06-12026-04-10-12026-04-05-1
permalink
felixrieseberg.com 2026-10-17-1

How to be more ambitious: A tutorial for humans with models

Rieseberg's tutorial reads as ambition advice, but every example that worked rested on a verifier. The crash-free app workflow needed crash-report access, version-to-commit mapping, and Windows, macOS and Linux machines to reproduce bugs, and his fourth prompt question asks what other than you or the model shows the result is right. He dates the outside-judge rule to October 2026, which makes it a workaround with an expiry, and the VAGEN paper is one attempt to build the real thing.

# tags
ambitionprompt-engineeringagentic-engineeringhuman-ai-interactionverifier-bottleneckself-grading-agentsai-practitionerblog-postclaudemulti-agent-orchestration
◆ entities
Prompt EngineeringIndependent verificationWorkflow embeddingVerifier-bottleneckMulti-agent orchestration
→ threads
verifier-bottleneck
⟷ links
2026-05-07-22026-04-17-w22026-04-05-12026-04-11-12026-03-13-12026-04-15-22026-04-07-22026-04-07-12026-03-13-w32026-04-17-w3
permalink
YouTube (Corey Gallon, Rexmore) 2026-10-14-1

I Believe Everything My Agents Tell Me: Three Levels of Review — Corey Gallon, Rexmore

Gallon's agent produced a letter whose numbers were right to the cent and whose premise was wrong, which is exactly the failure reconciliation can't see. Only the role-based cold reviewers attacked the frame; the invoice check would have passed it. In about 4 in 10 analysed 2026 sessions an agent got something wrong that mattered, so self-reported completion plus a spot-check is no longer a defensible default, and verification effort will have to scale with stakes.

# tags
verification-infrastructureverifier-bottleneckagent-evaluationself-grading-agentsmaker-checkerclosed-loop-verificationagent-orchestrationai-engineeringai-practitioneryoutubevideo
→ threads
verification-infrastructureverifier-bottleneckagent-orchestration
⟷ links
2026-05-01-w32026-04-30-32026-05-22-w22026-05-07-22026-04-05-12026-05-10-32026-05-06-32026-05-06-1
permalink
Anthropic Engineering 2026-10-14-3

Redesigning source control at Anthropic

Anthropic's merge queue stopped working once merged changes went from about 2,500 a day in May to over 30,000 in September, so the gate moved to post-merge testing and agent conflict repair. That swaps a process control for a bet on agent competence, and the post doesn't publish failure data to show the bet is safe. Checkout, CI and merge are the next layers to be rebuilt as server-side services, since 25 million daily CI checkouts can't be fetched like a human would.

# tags
anthropiccoding-agentsagentic-engineeringdeveloper-toolsci-velocitycode-reviewagent-infrastructureverifier-bottleneckworkflow-inversionai-practitionermythos
→ threads
coding-agentsverifier-bottleneck
⟷ links
2026-04-04-22026-04-05-22026-04-24-w22026-04-09-22026-04-01-32026-04-17-w12026-04-09-32026-03-09-22026-03-12-3
permalink