Prithivi Da

Founding CTO @ MeltPlan, 50M+ downloads in 🤗, Cited in NeurIPS, IEEE/CVF, ACL

[Prithivi Da @prithivida]

https://t.co/jgBsYDLAFI

[Prithivi Da @prithivida]

Awesome - a dynamic workflow specific harness that can orchestrate tool calls from a library of tools sound like the best next step.

[Thariq @trq212]

https://t.co/R6exTuF7P8

[Prithivi Da @prithivida]

@pcshipp building...

building reliable systems >> writing code.

[Prithivi Da @prithivida]

@andersonbcdefg And Libraries had the decency to split fiction from non-fiction. “Data centers” lost that…

[Prithivi Da @prithivida]

@djcows 😂

[Prithivi Da @prithivida]

@andersonbcdefg Wow you make your own Japanese style curry :)

[Prithivi Da @prithivida]

@dianetc_ Brilliant ! Thanks for sharing 🙏

[Prithivi Da @prithivida]

@NirantK Try a pair of Meta RBs or Oakleys. Your respect will stop at the ad. Junk ! (I own a Meta RB).

[Prithivi Da @prithivida]

@antoine_chaffin @lateinteraction @Robro612 @hugemensa Might interest you:

[Prithivi Da @prithivida]

FastLane for Late-Interaction.

https://t.co/luPbfB71JB

[Prithivi Da @prithivida]

FastLane for Late-Interaction.

https://t.co/luPbfB71JB

[Prithivi Da @prithivida]

@tunguz Haha nicely done !

[Prithivi Da @prithivida]

@ardabrowski @glcst @tursodatabase True, it’s hard to run out. worst case is collisions.

but I won’t call it garbage, possibly good marketing :)

[Prithivi Da @prithivida]

@henrythe9ths I thought Instagram CTO joined as a CPO.

[Prithivi Da @prithivida]

@glcst Assuming uuid4 till 99m the p(collision) = 0, is there something else bothering you 🤔 ?

[Prithivi Da @prithivida]

@NirantK Why don’t we do make this real, when your APIs are ready give me like a beta access along with your eval set queries. Let me run with what I am building and share time, cost and response we can compare…

That works ?

[Prithivi Da @prithivida]

1. Having a large library of tools ain’t tool explosion, infact it’s inevitable if you have a thriving ecosystem of agents. Some tools might be shared.

2. Having a lot of tools hot in model context is a problem.

3. And you don’t have to. (Low key you don’t even need MCP.)

(If you squint, tools (APIs in your case) are just one abstraction of capabilities (more dev friendly) we can add to an agent and skills (say a MD file) are a different abstraction of capabilities(more layperson friendly).

Openclaw and clawhub fx, the hub might have 1000s of skills. Would you say they have a skills explosion problem just for having a large hub. They don’t inject it all into the system prompt and keep them hot. (Albeit will admit in this case end user needs to install skills and that’s bad for your usecase).

You don’t need it to be a hot list and you don’t need the users to install it. That’s the best middle ground :)

To be continued ..

[Prithivi Da @prithivida]

@antoine_chaffin would happily partake.

[Prithivi Da @prithivida]

@NirantK You can’t be mad at douchebags :), take it easy let’s ship that well sought after harness. Albeit frontier LLMs are not the only kind of models we can ship.

[Prithivi Da @prithivida]

Tool Search Tool as a meta tool for searching tools exists. Anthropic released it for their ecosystem before PTC programmatic tool call. Dynamic tool composition is not a leap if you can search tools reliably for a query. Since TST was locked to one ecosystem @andersonbcdefg wrote an implementation on dynamic composition across providers and wrote a blog about (if my memory serves).

“Nobody knows what that means” seems like a projection of yours and that possibly gets you going :)

[Prithivi Da @prithivida]

I would argue tools are akin to ingredients and skills are akin to recipes. As frontier moves LLMs will cook with their own recipes i.e. we can leap to Dynamic Tool Composition with retrieval confined to Tool searches (on a large tool library which external tool makers will bring) . So skills and skill search will be subsumed at worst or reserved only for non-frontier models at best.

[Jo Kristian Bergum @jobergum]

Progressive disclosure and skill is a big part of agent harness engineering.

Effective retrieval over skills is going to be big, might even become "web scale".

"Under this paradigm, we propose Skill Retrieval Augmented Agents (SR-Agents), which dynamically retrieve and use relevant skills from large-scale skill corpora to expand their problem-solving capabilities"

https://t.co/dIETJBAUQg