正在加载视频...

视频加载失败

Hate getting rate limited in the middle of an intense agent coding session? With Clawdi <> Filecoin skill, we never worry about it, as we can start in another model with the same context.

94,409 次观看 • 1 个月前 •via X (Twitter)

10 条评论

Filecoin 的头像
Filecoin1 个月前

Give your agents persistent memory with our skill today npx skills add FIL-Builders/filecoin-clawdi --skill filecoin-clawdi-setup

Filecoin 的头像
Filecoin1 个月前

Want to learn more about Filecoin Agent Skills? Meet us this week in NYC. Storage is a Skill Salon - reserve your spot 👇

cryptowonder 的头像
cryptowonder1 个月前

This is really useful for developers. Being able to switch models and keep the same context means less stress and no need to start all over again.

DeFiMartial 的头像
DeFiMartial1 个月前

Getting rate limited mid-flow is the worst, tbh being able to switch models without losing context is a game changer.

ᏒᎴ ᏕᎥᎥᏁᎶᏂ 的头像
ᏒᎴ ᏕᎥᎥᏁᎶᏂ1 个月前

$FIL

Ralph_wiggum 的头像
Ralph_wiggum1 个月前

This is an absolute game-changer that eliminates all rate-limit frustrations and keeps your intense coding sessions flowing seamlessly forever!

I.M BUHARI 的头像
I.M BUHARI1 个月前

This deserves more eyes from the wider crypto space, #WEEX could easily bring that attention

The Optimist 的头像
The Optimist1 个月前

Rate limits shouldn’t kill momentum. Clawdi and Filecoin make agent workflows portable, so you can switch models without losing valuable context.

gwom 的头像
gwom1 个月前

Rate limits hitting mid-flow is the worst kind of context death. Sealing the session on Filecoin and picking it up in another model is the right move the work stays portable instead of trapped in one vendor’s window. That’s how agent sessions should actually work.

Mr Moe 的头像
Mr Moe1 个月前

Love how Clawdi with the Filecoin skill lets you seamlessly switch models mid-session without losing any context no more rate-limit frustration!

相关视频

An overview of how we think about context graphs at Harvey. Context graphs are a promising direction for improving agent quality and efficiency. We ran a series of experiments on Legal Agent Bench to evaluate how structured context improves online agent performance. For each LAB task we evaluated, an agent first reviews each document in its client matter and builds a graph of relevant entities and their relationships – e.g. parties, dates, draft vs. executed status, which versions belong to the same contract. To evaluate the impact of the graph, we compared the performance of an agent with and without the context graph, using LAB’s standard grading setup. Overall, the agent with the context graph improved rubric pass rate by up to 30% while reducing task cost by up to ~50%. In some cases the graph led to massive improvements. For example, in one firm-knowledge task, the agent was asked to find the firm’s most recent secured financing and retrieve the executed credit and security agreements as precedents for a new facility. An agent working from raw files attempted to search through several files sequentially, and looked at many different matters, but ultimately selected the wrong precedent (0% of rubric criteria). With the context graph, the same agent found the relevant matter and its executed agreements immediately (75% of rubric criteria). We’ll have more to share soon on how we’re building this into Harvey, along with more experiments like this one!

Niko

72,789 次观看 • 26 天前