HackerTrans
TopNewTrendsCommentsPastAskShowJobs

nijaar

no profile record

Submissions

MCP Dockmaster - MCP UI Manager is live (open-source)

mcp-dockmaster.com
4 points·by nijaar·letztes Jahr·1 comments

LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of O1 on PlanBench

arxiv.org
2 points·by nijaar·vor 2 Jahren·1 comments

comments

nijaar
·vor 9 Monaten·discuss
for a sec i thought DEI was going too far

is the title like that on purpose?
nijaar
·letztes Jahr·discuss
MCP Dockmaster is a straightforward tool designed to help you easily install, manage, and monitor AI applications using MCP.

MCP is an open-source standard created by Anthropic that allows AI apps like Claude Desktop or Cursor to seamlessly access data from platforms such as Slack or Google Drive, interact with other applications, and connect to APIs.

Next stop, we want to add payment integrations so it is easier to monetize using MCPs.

Any feedback is very welcomed!
nijaar
·letztes Jahr·discuss
same here. pro in the US and still no access. i even logged in using my phone and a different browser
nijaar
·vor 2 Jahren·discuss
This is from 2014. What’s the point of resharing it?
nijaar
·vor 2 Jahren·discuss
"The ability to plan a course of action that achieves a desired state of affairs has long been considered a core competence of intelligent agents and has been an integral part of AI research since its inception. With the advent of large language models (LLMs), there has been considerable interest in the question of whether or not they possess such planning abilities. PlanBench, an extensible benchmark we developed in 2022, soon after the release of GPT3, has remained an important tool for evaluating the planning abilities of LLMs. Despite the slew of new private and open source LLMs since GPT3, progress on this benchmark has been surprisingly slow. OpenAI claims that their recent o1 (Strawberry) model has been specifically constructed and trained to escape the normal limitations of autoregressive LLMs--making it a new kind of model: a Large Reasoning Model (LRM). Using this development as a catalyst, this paper takes a comprehensive look at how well current LLMs and new LRMs do on PlanBench. As we shall see, while o1's performance is a quantum improvement on the benchmark, outpacing the competition, it is still far from saturating it. This improvement also brings to the fore questions about accuracy, efficiency, and guarantees which must be considered before deploying such systems."
nijaar
·vor 2 Jahren·discuss
great explanation. thank you!
nijaar
·vor 2 Jahren·discuss
if it is smaller, doesn't it mean that it has less code to execute hence should it be faster? Trying to understand better -- this is something completely new for me
nijaar
·vor 2 Jahren·discuss
if this works would this make the rust compiler considerably smaller / faster?
nijaar
·vor 2 Jahren·discuss
It could be even easier, we implemented a two click install open-source local AI manager (+RAG and other cool stuff) for Windows / Mac / Linux. You can check it out in shinkai com or check out the code in https://github.com/dcspark/shinkai-apps
nijaar
·vor 2 Jahren·discuss
Are they planning to acquihire Taiwan?
nijaar
·vor 3 Jahren·discuss
Not really bc the IRS actually has puts guidelines (although kind of slow) for crypto unlike the SEC
nijaar
·vor 3 Jahren·discuss
For mobile it may be very important performance for some cases (too repetitive or just heavy load) so using Rust allows to compile to the specific mobile architecture. The same is not possible with typescript which just run in the JSVirtualMachind