Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Complex Systems with Patrick McKenzie (patio11)

Complex Systems with Patrick McKenzie (patio11) artwork

Getting better at LLMs, with Zvi Mowshowitz

Jun 12, 202552 minAudio

In this episode, Patrick McKenzie (patio11) recorded with Zvi Mowshowitz (TheZvi) live at the LessOnline conference. They explore practical strategies for getting better results from large language models. Zvi explains how to customize AI behavior through thoughtful system prompts, while Patrick shares techniques for using LLMs as writing partners and research assistants. They discuss the evolving relationship between content creators and AI training data, touching on the emerging field of "generative engine optimization" (GEO). The conversation also covers multimodal capabilities, recursive AI use, and strategies for avoiding common failure modes like hallucination and sycophancy. - Full transcript: www.complexsystemspodcast.com/getting-better-at-llms-with-zvi-mowshowitz/ - Sponsor: Vanta Vanta automates security compliance and builds trust, helping companies streamline ISO, SOC 2, and AI framework certifications. Learn more at https://vanta.com/complex - Links: Don’t Worry About the Vase https://thezvi.wordpress.com/ - Timestamps: (01:08) Understanding system prompts (02:04) Customizing LLM behavior (05:58) Memory features in LLMs (10:21) Generative Engine Optimization (GEO) (15:59) Sponsor: Vanta (17:17) Art and AI: Enhancing creativity (20:36) Recursive use of AIs (25:22) Addressing LLM frustrations (27:05) Checking for hallucinations in AI outputs (28:11) Experimenting with AI models (29:44) Optimizing AI prompts and outputs (31:19) Using AI for writing and editing (32:32) AI as a research and writing partner (33:26) Prompting AI and humans effectively (39:39) Balancing AI assistance with personal voice (51:03) Wrap

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Hosts

  • Patrick McKenzie Host Feed-stated

Guests

  • Zvi Mowshowitz Guest Feed-stated

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. Liquidating a whale by hand, 22 times

    Nov 12, 202622 minAudio

    Patrick McKenzie (patio11) reads his 2022 Bits About Money essay demystifying financial leverage, starting from the balance sheet math that lets you work out in your head how big a drop in asset value wipes out a firm’s...

    Credit the people on this episode

  2. Reading the Anthropic S-1, with Zvi Mowshowitz

    Nov 6, 20261 hr 20 minAudio

    Patrick McKenzie (patio11) is joined by returning guest Zvi Mowshowitz, AI watcher extraordinaire, to read Anthropic’s S-1 and what it shows about the AI industry. They cover a founder-controlled structure built on a...

    Credit the people on this episode

  3. Why SoftBank paid me 17 yen to skip the air conditioning

    Oct 29, 202627 minAudio

    Patrick McKenzie (patio11) reads his 2022 Bits about Money essay “Markets in power,” prompted by a SoftBank push notification asking him to cut his air conditioner use between 5 and 8 PM, and updated for the era of AI...

    Credit the people on this episode

  4. The charity that is also a time machine

    Oct 22, 202627 minAudio

    Patrick McKenzie (patio11) reads his 2022 Bits about Money essay on the infrastructure behind American charitable giving, prompted by the wave of AI-generated wealth expected to flow into philanthropy. He explains...

    Credit the people on this episode

  5. ⁠⁠The $900 million wire that wasn't final

    Oct 8, 202633 minAudio

    Patrick McKenzie (patio11) reads his 2022 Bits about Money essay "Finality does not exist in payments." It argues that how final a payment is depends on the rails, the parties, and the governing law, not on the payment...

    Credit the people on this episode