Kaushik GopalUnclaimed
Host of Fragmented - AI Developer Podcast.
1 Feed-stated
Counts Verified and Feed-stated credits: what a show's own feed states, or a confirmation backs. See the record
- Host
Claim this profile Add a creditIs this you? Claiming needs a free account. You sign in or join, then come straight back here.
This profile is unclaimed. PodSubs built it from public show feeds and credits. The person it is about has not reviewed it yet.
About
Kaushik hosts Fragmented - AI Developer Podcast.
Written by PodSubs from Kaushik's credits.
PodCred record
PodCred is the verified record of where Kaushik has worked and appeared. These credits come from the shows' own feeds and wait for people who were there to confirm them.
Worked with Kaushik on a show? This is where you give them credit.
Shows they work on now
1 show
Is an appearance missing?
People get invited back because someone remembered they were great. If you heard this person on a show and it is not listed here, add it. Your memory might be the reason they get their next invitation.
No account needed. Anyone can give a credit.
Experience, education, skills, and recommendations start empty. They fill in when Kaushik claims this profile.
Recommendations
No recommendations for Kaushik yet.
Recommendations open once Kaushik claims the profile.
Activity
0 followers
No posts yet. Posts Kaushik shares on PodSubs, and what Kaushik publishes on Substack, YouTube and elsewhere, will show here.
Recent episodes
From the shows they work on now
312 - Understanding Pi Durable with Mario & Armin of Earendil
Fragmented - AI Developer Podcast
What does it take to keep an agent working after its process dies? Pi creator Mario Zechner and Earendil co-founder Armin Ronacher join KG to explain Pi Durable: explicit tasks, crash recovery, and the primitives for...
311 - Self learning harnesses are here
Fragmented - AI Developer Podcast
Claude Code and Codex have been the mainstay agent harnesses, with OpenCode and Pi as the popular open-source alternatives. But two new entries are pushing what a harness even is: DeepSeek's Cordis kernel, where...
310 - Mitchell Hashimoto on Ghostty & His Agentic Coding Workflow
Fragmented - AI Developer Podcast
Mitchell Hashimoto co-founded HashiCorp, built some of the most impressive DevOps tools like Vagrant and Terraform, sold the company to IBM - and then built a terminal. Ghostty is now where a huge chunk of agentic...
309 - Background Agents
Fragmented - AI Developer Podcast
Andrej Karpathy says the goal is to maximize how long an agent runs without your intervention. But there's a false summit most teams hit first: individual speed goes up while system speed stalls, your laptop roars under...
308 - How Image Diffusion Models Work - the 20 minute explainer
Fragmented - AI Developer Podcast
You already know how LLMs work from our popular 20-minute explainer. Now we take it to images. What does Michelangelo have to do with stable diffusion? More than you'd think. Walk away knowing how image generation...
307 - Harness Engineering - the hard part of AI coding
Fragmented - AI Developer Podcast
The hard part of AI coding isn't generating code - it's controlling quality, safety, and drift. Kaushik and Iury break down harness engineering: the five pillars for shaping an agent's environment and what it looks like...
306 - Keeping your agent instructions in sync and effective
Fragmented - AI Developer Podcast
AGENTS.md is becoming the common language for AI coding tools, but keeping repo rules, personal rules, and tool-specific files in sync is still messy. In this episode, Kaushik and Iury break down the sync problem,...
305 - Subagents explained - What they are, when (not) to spawn them
Fragmented - AI Developer Podcast
Subagents are becoming a core primitive for serious AI-assisted development. In this episode, Kaushik and Iury disambiguate "agent" terminology, unpack plan mode vs subagents, and explain how parallel, scoped workers...
304 - Agent Skills - when to use them and why they matter
Fragmented - AI Developer Podcast
Agent Skills look simple, but they are one of the most powerful building blocks in modern AI coding workflows. In this episode, Kaushik and Iury break down when to use skills, how progressive disclosure works, and how...
303 - How LLMs Work - the 20 minute explainer
Fragmented - AI Developer Podcast
Ever get asked "how do LLMs work?" at a party and freeze? We walk through the full pipeline: tokenization, embeddings, inference - so you understand it well enough to explain it. Walk away with a mental model that you...
