Semi Doped Podcast Transcripts
Vikram Sekar and Austin Lyons · 42 episodes with transcripts
The business and technology of semiconductors. Alpha for engineers and investors alike.
Spoken has transcripts of 42 Semi Doped episodes, with the speakers named. The newest listed here is from February 6, 2026.
Every Semi Doped transcript in one script
42 episodes of Semi Doped have transcripts. Fetch them all as speaker-labeled Markdown in one script — 1 credit each, and re-fetching one you already have is free:
curl -s -H "x-api-key: YOUR_KEY" \
https://spoken.md/podcasts/1866707196/episodes \
| jq -r '.episodes[] | "\(.id) \(.title)"' \
| while IFS=' ' read -r id title; do
slug=$(echo "$title" | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9' '-' | sed 's/-*$//')
[ -f "${id}-${slug}.md" ] && continue
curl -sf -H "x-api-key: YOUR_KEY" \
-o "${id}-${slug}.md" \
https://spoken.md/transcripts/$id || rm -f "${id}-${slug}.md"
sleep 0.34
doneAlready-saved files are skipped — safe to re-run after a top-up.
Latest Semi Doped transcripts
A New Era of Context Memory with Val Bercovici from WEKA
February 6, 2026
Val Bercovici (0:00)
100,000 tokens, one megabyte of data, translates to 50 gigabytes of KVCache working memory. And that's because you're vectorizing, you're adding 10 to 20,000 dimensions of intelligence to this 100,000 tokens, this one megabyte of data. So if one megabyte equals 50 gigabytes, and that's just at the beginning of one…
Vikram Sekar (0:28)
Welcome to the Semi Doped Podcast. I'm Vikram from VIX Newsletter on Substack, and with me is a special guest today, Val Bercovici, Chief AI Officer at Weka. Weka is a California based technology company that provides an AI native data platform designed to solve the massive data bottlenecks found in modern…
Val Bercovici (1:11)
Really good. Excited to be here. Very enthusiastic new fan of the newsletter.
These are examples, not the full list — see everything available from this show via the API, get started.
Looking for a different show? Search for it to see whether it has transcripts you can fetch.
Thousands of transcripts fetched by people building searchable podcast archives
Any Semi Doped episode comes back as Markdown with the speakers named, one credit each.
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000748541353No subscription. Credits never expire. Prices exclude VAT, added at checkout for EU customers. Try free with pt_demo.