--- schema: 1 type: video title: 'RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI' description: >- Large codebases break coding agents: they lose the architecture and drown in tool output as context grows. This talk introduces Recursive Language Models (RLM) from a MIT paper a pattern that loads the repo into a programmable REPL where the model writes code to inspect it and recursively delegates focused sub-questions via llm_query. With a live demo on RLM Code (independent, unofficial), you'll see the loop run end to end on local and cloud models, with a fully inspectable trajectory. Speakers: - Shashi (Superagentic AI): Building tools and frameworks for AI Agents X/Twitter: https://x.com/Shashikant86 LinkedIn: https://www.linkedin.com/in/shashikantjagtap/ GitHub: https://github.com/Shashikant86 --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/8oyalrfwgjw-rlm-recursive-language-models-for-large-codebases Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: 'https://liquidgold.cc/watch/8oyalrfwgjw' markdown: 'https://liquidgold.cc/watch/8oyalrfwgjw.md' llms: 'https://liquidgold.cc/watch/8oyalrfwgjw/llms.txt' parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T07:51:20.729Z' language: null children: [] videoId: 8oyalrfwgjw durationSeconds: 1047 publishedAt: '2026-07-12T23:00:06.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 10 endSeconds: 99 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=10' heldReason: rights - ordinal: 1 text: null startSeconds: 10 endSeconds: 99 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=10' heldReason: rights - ordinal: 2 text: null startSeconds: 110 endSeconds: 213 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=110' heldReason: rights - ordinal: 3 text: null startSeconds: 110 endSeconds: 213 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=110' heldReason: rights - ordinal: 4 text: null startSeconds: 225 endSeconds: 331 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=225' heldReason: rights - ordinal: 5 text: null startSeconds: 225 endSeconds: 331 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=225' heldReason: rights - ordinal: 6 text: null startSeconds: 344 endSeconds: 449 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=344' heldReason: rights - ordinal: 7 text: null startSeconds: 344 endSeconds: 449 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=344' heldReason: rights - ordinal: 8 text: null startSeconds: 461 endSeconds: 564 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=461' heldReason: rights - ordinal: 9 text: null startSeconds: 575 endSeconds: 685 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=575' heldReason: rights - ordinal: 10 text: null startSeconds: 697 endSeconds: 787 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=697' heldReason: rights - ordinal: 11 text: null startSeconds: 797 endSeconds: 909 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=797' heldReason: rights - ordinal: 12 text: null startSeconds: 922 endSeconds: 1047 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=922' heldReason: rights - ordinal: 13 text: null startSeconds: 922 endSeconds: 1047 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=922' heldReason: rights - ordinal: 14 text: null startSeconds: 922 endSeconds: 1047 watch: 'https://liquidgold.cc/watch/8oyalrfwgjw?t=922' heldReason: rights --- # RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI Large codebases break coding agents: they lose the architecture and drown in tool output as context grows. This talk introduces Recursive Language Models (RLM) from a MIT paper a pattern that loads the repo into a programmable REPL where the model writes code to inspect it and recursively delegates focused sub-questions via llm_query. With a live demo on RLM Code (independent, unofficial), you'll see the loop run end to end on local and cloud models, with a fully inspectable trajectory. Speakers: - Shashi (Superagentic AI): Building tools and frameworks for AI Agents X/Twitter: https://x.com/Shashikant86 LinkedIn: https://www.linkedin.com/in/shashikantjagtap/ GitHub: https://github.com/Shashikant86 --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/8oyalrfwgjw-rlm-recursive-language-models-for-large-codebases Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/watch/8oyalrfwgjw · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks --- #### Chunk 0: Document excerpt (0:00 to 1:39) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 1: Document excerpt (1:39 to 3:33) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 2: Document excerpt (3:33 to 5:31) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 3: Document excerpt (5:31 to 7:29) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 4: Document excerpt (7:29 to 9:24) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 5: Document excerpt (9:24 to 11:25) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 6: Document excerpt (11:25 to 13:07) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 7: Document excerpt (13:07 to 15:09) > Held: transcript rights do not permit this chunk's text. --- #### Chunk 8: Document excerpt (15:09 to 17:27) > Held: transcript rights do not permit this chunk's text.