Savlar4 sources healthy · latest episode 15 Oct 2026
Sources

Four shows feed the brief

30 of 831 episodes processed. Each active show is checked for new episodes every 30 minutes, and an episode reaches the brief only once every stage below has passed.

Shows

checked every 30 min while active

  • Dwarkesh PodcastDwarkesh Patel · Podcast feed
    Episodes:12 processedlatest 1 Oct 2026
    Transcripts:Transcribed 12of 142 episodes
    Last checked:17:16 todaynext in 11 min
    Healthy
  • Latent Space: The AI Engineer PodcastLatent.Space · Podcast feed
    Episodes:7 processedlatest 14 Oct 2026
    Transcripts:Transcribed 7of 235 episodes
    Last checked:17:16 todaynext in 11 min
    Healthy
  • Machine Learning Street Talk (MLST)Machine Learning Street Talk (MLST) · Podcast feed
    Episodes:6 processedlatest 10 Oct 2026
    Transcripts:Transcribed 6of 271 episodes
    Last checked:17:16 todaynext in 11 min
    Healthy
  • No Priors: Artificial Intelligence | Technology | StartupsConviction · Podcast feed
    Episodes:5 processedlatest 15 Oct 2026
    Transcripts:Transcribed 5of 183 episodes
    Last checked:17:16 todaynext in 11 min
    Healthy

Add a source

Adding or checking a source starts paid model work, and pausing one stops it, so changes need the admin password.

Sign in to make changes

From audio to signal

What the brief rests on, across every episode. Most of what is said never becomes a signal, on purpose: the brief would rather miss a pattern than show a wrong one.

  1. 1 · Transcribe42 hof audio
  2. 2 · Attribute82%of speech attributed to a named speaker, none of it guessed
  3. 3 · Extract10314claims, each tied to a quote and a timestamp

Episodes

newest first · hover a segment for its stage

PublishedEpisodeLengthTranscriptSpeakers namedClaimsStages
15 Oct 2026The Changing Physics of Cybersecurity and Drug Development with OpenAI President Greg BrockmanNo Priors: Artificial Intelligence | Technology | Startups39:22TranscribedElad, Sarah, Greg15114 of 14
14 Oct 2026Lab-in-the-Loop at Compute Speed — Ian Quigley, Leash BioLatent Space: The AI Engineer Podcast · in the backlog, not processed1:49:56none yetnone yet00 of 14
13 Oct 2026Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna RoboticsLatent Space: The AI Engineer Podcast1:11:57Transcribedswyx, Vibhu, Jason27214 of 14
10 Oct 2026What Most People Get Wrong About Evolution | Akarsh KumarMachine Learning Street Talk (MLST) · in the backlog, not processed47:54none yetnone yet00 of 14
10 Oct 2026Why AlphaFold Didn't Solve Protein Folding — Pushmeet Kohli, Google DeepMind & Sal Candido, BiohubLatent Space: The AI Engineer Podcast · in the backlog, not processed31:56none yetnone yet00 of 14
9 Oct 2026Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha LaskinNo Priors: Artificial Intelligence | Technology | Startups1:09:44TranscribedElad, Sarah, Misha26014 of 14
8 Oct 2026Synthesis Superintelligence: from Semiconductors to Superconductors — Periodic Labs’ Liam Fedus and Ekin Dogus CubukLatent Space: The AI Engineer Podcast1:24:00Transcribedswyx, Ekin, Liam35914 of 14
2 Oct 2026Frontier Chips for Frontier AI Labs, with Walter Goodwin, Founder/CEO of FractileNo Priors: Artificial Intelligence | Technology | Startups35:38TranscribedSarah, Walter14114 of 14
2 Oct 2026Academia is for Ambition — Alex Zhang, MITLatent Space: The AI Engineer Podcast1:41:28Transcribedswyx, Alex32214 of 14
1 Oct 2026How a Voice Agent Learns the Rhythm of Conversation — Shawn WenMachine Learning Street Talk (MLST) · in the backlog, not processed1:10:09none yetnone yet00 of 14
1 Oct 2026Si Sheppard – How did a few hundred Spanish soldiers topple two empires?Dwarkesh Podcast1:37:23TranscribedDwarkesh, Si50714 of 14
30 Sept 2026Why Dwarkesh is Wrong about Computer Use + How OpenAI shipped its Jev competitor in 1 WeekLatent Space: The AI Engineer Podcast39:12Transcribedswyx, Ari, Nikunj16014 of 14
30 Sept 2026Who Checks a Proof No Human Can Read? — Leo de MouraMachine Learning Street Talk (MLST) · in the backlog, not processed1:14:19none yetnone yet00 of 14
29 Sept 2026Claude Code’s Next Era — Thariq Shihipar, AnthropicLatent Space: The AI Engineer Podcast1:32:29Transcribedswyx, Thariq29314 of 14
26 Sept 2026When AI Research Starts Moving Faster Than Human Research - Zhengyao JiangMachine Learning Street Talk (MLST)43:42TranscribedTim, Zhengyao15214 of 14
25 Sept 2026OpenRouter: from Seed to Stripe — with OpenRouter’s Alex Atallah & AMP’s Anjney MidhaLatent Space: The AI Engineer Podcast · in the backlog, not processed1:20:43none yetnone yet00 of 14
25 Sept 2026Runway’s WorldPrompt and the Engineering of Real-Time WorldsLatent Space: The AI Engineer Podcast · in the backlog, not processed1:36:21none yetnone yet00 of 14
24 Sept 2026Re-Founding Incumbents for the AI Era with Sequence Holdings Co-Founder and CEO Michael LeeNo Priors: Artificial Intelligence | Technology | Startups · in the backlog, not processed42:44none yetnone yet00 of 14
23 Sept 2026How Deep Learning Finally Cracked Messy Tables - Frank HutterMachine Learning Street Talk (MLST) · in the backlog, not processed1:53:12none yetnone yet00 of 14
23 Sept 2026🔬Bio-security is an AI Arms Race - Eric Nguyen (CEO, Radical Numerics)Latent Space: The AI Engineer Podcast · in the backlog, not processed1:31:58none yetnone yet00 of 14
22 Sept 2026🔬 An Oscar, Two Asteroids, and the Algorithm in Your sklearn: John Platt on AI for ScienceLatent Space: The AI Engineer Podcast · in the backlog, not processed2:01:26none yetnone yet00 of 14
21 Sept 2026Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AILatent Space: The AI Engineer Podcast · in the backlog, not processed2:20:53none yetnone yet00 of 14
21 Sept 2026Why Scaling Prediction Cannot Create Intelligence - Alexander MattickMachine Learning Street Talk (MLST)2:14:20TranscribedTim, Alexander61614 of 14
18 Sept 2026Why Diffusion Will Win AI Inference with Inception Co-Founder and CEO Stefano ErmonNo Priors: Artificial Intelligence | Technology | Startups38:13TranscribedSarah, Stefano18814 of 14
17 Sept 2026Noam Brown – Agent swarms, alignment, & recursive self-improvementDwarkesh Podcast1:20:10TranscribedDwarkesh, Noam39814 of 14

A failed stage turns its segment red and stops the stages after it. Running a stage again never duplicates what it already wrote. All 831 episodes →