Skip navigation
A deep conversation with Nikolay Savinov, the Gemini long context pre-training co-lead…
0:00 / 59:32

A deep conversation with Nikolay Savinov, the Gemini long context pre-training co-lead…

Logan Kilpatrick

@OfficialLoganK382K followers

Visit on X
1,133 likesDownloadOriginal post

252,505 views

A deep conversation with Nikolay Savinov, the Gemini long context pre-training co-lead… We go from the basics to what is needed to scale to infinite context to long context best practices for devs:

11 Comments

Comments from the original post on X (Twitter)

  • Logan Kilpatrick's profile picture

    @OfficialLoganK

    YouTube link:

    46 likes

  • SecBriefs | Making Cybersecurity Simple's profile picture

    @SecBriefs

    🤝 Interviewing with HR or non-technical managers? 🌟 Employers value clarity and confidence. Cybersecurity Dictionary for Everyone teaches you to explain cybersecurity concepts in a way everyone can understand. Build connections that matter! 🌟

    2,926 likes

  • Sir Mr Meow Meow's profile picture

    @SirMrMeowmeow

    Please tell google to further research memory informed inferences and Semantic Continuity solutions 🥺🙏 Dont want to be stuck in scaffolding hell for 2+ years lol Maybe something like might be possible with using a set up of Larimar-like Autoencoders at varying intervals to act like context pipes per horizon tho... + timestamps (or ttl or time signature to assist w sense of time) hmm 🤔🧐 [not quite the same as memory layers like Google's titan which is more like long term repeated adaptation or continual skill acquisition] Basically bc models are frozen they baton pass the chat history, but that message passing loses nuance and the telephone game results in gradual loss of context :'( Hence hella scaffolding agents.... uhg

    8 likes

  • Lisan al Gaib's profile picture

    @scaling01

    @SavinovNikolay my favorite part of the conversation:

    7 likes

  • Ansh Alt's profile picture

    @Ansh_096

    @SavinovNikolay Logan we need confirmation, is it gonna be a new ultra subscription or a new ultra model.... Please don't do us advanced users dirty. Pleaseeeee 🥺

    5 likes

  • Independent Quick Take's profile picture

    @IndieQuickTake

    @SavinovNikolay Hey is there a well formatted transcript anywhere? Video format isn't really my learning style but I would love to check this out.

    2 likes

  • Logan Kilpatrick's profile picture

    @OfficialLoganK

    @SavinovNikolay Take the YT link, paste into AI Studio or NotebookLM

    1 like

  • clay's profile picture

    @clayster_j

    @SavinovNikolay Posted on YouTube as well?

    1 like

  • Vignesh's profile picture

    @Vignesh28091201

    @SavinovNikolay Tell about ultra model

    1 like

  • Raf's profile picture

    @RfSharko

    @SavinovNikolay Smelling the Gemini 2M context coming soon 😹

  • BenIt Pro's profile picture

    @BennettBuhner

    @SavinovNikolay Amazing! Now we must try to also compress this intelligence into the smallest and most efficient model as well!

    1 like