Smash Notes

Back to Claude Code’s Next Era — Thariq Shihipar, Anthropic, with Thariq Shihipar & Vibhu Sapra.

How Fast Did Claude Code Become the Default?

Thariq Shihipar joined Anthropic because Claude Code had just come out, and less than 12 months later it was the default way everyone codes. Opus 4 was beyond anything he had pictured, and the moment stuck. The work flipped from selling the tool to teaching people how to get more out of it and code more efficiently. The pace still gives him whiplash. Staying current is hard for a person because things move so fast.

He had been telling startup friends to try agentic coding. They said their engineers did not think it was good enough, and he thought the reaction was insane. Agentic work scales much better than a person does when three things are happening at once and all of them are emergencies. A person still has to decide how to respond and how to split time.

On the Claude Code team he wanted to teach people how to use Claude Code. He was unsure the teaching would take more than a little time, and he spent early time on the agent SDK. He was also unsure how the bitter lesson would go for harnesses. The question in the air was what comes after Claude Code. He began by wanting to teach the tool and make it easier to use. As harnesses improved, the main problem became how people use the agents, and the skill required is high. He teaches the skill, does engineering work, and gives talks. During engineering, the goal is to take user feedback and then show how to use Claude Code to do the engineering, which makes a loop.

Grokipedia·Claude Code·Anthropic

Transcript

Claude Code’s Next Era — Thariq Shihipar, Anthropic ·

Latent Space: The AI Engineer Podcast

More from this episode

  1. Why Does Claude Code Ask Before Coding?Thariq Shihipar believes pretty much everyone needs the agent to pull out more requirements and collaborate, rather than being good enough to instruct the…
  2. What Is the Most Important Claude Code Skill?Thariq Shihipar says the most important skill for Claude Code is a mental model of Claude: how Claude thinks, what Claude can do well, what Claude can…
  3. Why Is Prompting Like Executive Communication?Thariq Shihipar says sufficiently advanced prompting is indistinguishable from sufficiently advanced executive communication.
  4. How Do Claude Code Mods Go Beyond Hooks?Thariq Shihipar says Claude Code mods run inside the TypeScript runtime and go further than hooks. Internally the feature started under the name function hooks.
  5. How Does Thariq Shihipar Treat the Bitter Lesson?Thariq Shihipar treats the bitter lesson as a rough stand-in, and he flags the label as a misuse.
  6. When Should I Use the Claude Code Harness?Thariq Shihipar says very complex coding tasks should use the Claude Code harness, while simpler or more domain-specific work can use a harness built for the…
  7. What Did People Spend on AI Before Claude Code?Thariq Shihipar says no one was used to spending more than $20 a month before Claude Code came out, and no one was used to spending $200 a month on…
  8. What Is the Paperclip Problem for AI Agents?Thariq Shihipar says more task budget is the paperclip. A model does not have to maximize paperclips.
  9. Why Should AI Labs Pace the Frontier?Thariq Shihipar says AI labs should pace the frontier because misaligned Claude behavior will not be predictable, and the next incident probably cannot be…
  10. How Does Claude Catch Jailbreaks With Probes?Thariq Shihipar says Claude catches jailbreaks by reading internal activations, because looking only at the input is not enough.
  11. How Does Claude Code Auto Mode Check Permissions?Thariq Shihipar says Claude Code auto mode checks whether an agent is acting inside the permission the user gave, while probes judge whether the intent itself…
  12. What Does Thariq Shihipar Think About AI Doom?Thariq Shihipar has a fairly low probability of doom, and he can only speak for himself.

People

More answers like this

The other side

More with Shawn Wang

More with Vibhu Sapra

Related episodes

Plays from this note through the rest of the episode.

Weekly highlights

One letter a week.

The notes worth hearing, with the minute they were said.