echollama
Re:
on Thursday August 13, 2026 @01:24PM (#49289121)
finn is the goal of a self-balancing two-wheeled humanoid I'm building from scratch, mostly to force myself to learn a wide range of robotics.
firmware, cad, sim models, identification data and logs are all at https://github.com/Masony817/finn
-- things like cad files and such are in onshape so if you're interested just email me -- im intrigued to hear what others think outside of my own brains echo chamber so email me anything you want
Re:
on Thursday August 13, 2026 @12:27PM (#49288373)
finn is the goal of a self-balancing two-wheeled humanoid I'm building
from scratch, mostly to force myself to learn a wide range of robotics.
firmware, cad, sim models, identification data and logs are all at https://github.com/Masony817/finn
-- things like cad files and such are in onshape so if you're interested just email me -- im intrigued to hear what others think outside of my own brains echo chamber so email me anything you want
Re:Addictions Are Being Engineered
on Saturday June 28, 2025 @02:55PM (#44407179)
agreed its like saying that jerking off makes you healthier
The Incentive Structure That Makes Social Media Addiction Inevitable
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop ha...
on Friday June 06, 2025 @02:26PM (#44203631)
i fixed this
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop ha...
on Friday June 06, 2025 @12:12PM (#44202314)
yes it is
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop ha...
on Friday June 06, 2025 @02:07AM (#44198200)
would probably work better, this is just how i threw it together as an internal tool a long time ago. i just improved it and shipped it to opensource it.
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop ha...
on Friday June 06, 2025 @12:06AM (#44197728)
reasoning models know when they are close to hallucinating because they are lacking context or understanding and know that they could solve this with a question.
this is a streamlined implementation of a interanlly scrapped together tool that i decided to open-source for people to either us or build off of.
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop ha...
on Friday June 06, 2025 @12:04AM (#44197722)
this is mainly meant as a way to conversate with the model while you are programming with it. This is not meant to pull questions to a team but more to pair program. a markdown file is best for syntax in an llm prompt and also just easiest to have open and answer questions with. If i had more time and could i would build an extension into cursor.
Re:Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop ha...
on Friday June 06, 2025 @12:02AM (#44197711)
the reasoning aspect of most llms these days knows when its unsure or stuck, you can get that from its thinking tokens. It will see this mcp and call it when its in that state. Though this could benefit from some rules file to use it, although cursor doesn't quite follow ask for help rules, hence making this.
Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations
https://masonyarbrough.com/blog/ask-human
While building my startup i kept running into the issue where ai agents in cursor create endpoints or code that shouldn't exist, hallucinates strings, or just don't understand the code.ask-human-mcp pauses your agent whenever it’s stuck, logs a question into ask_human.md in your root directory with answer: PENDING, and then resumes as soon as you fill in the correct answer.the pain:your agent...
Re:Ask HN: Has anybody built search on top of Anna's Archive?
on Wednesday June 04, 2025 @01:01PM (#44182887)
garbled/half-hallucinated is probably what you would've gotten 8-12mo ago but now adays im sure with good prompting you can pull value from any book.
Re:The future of MCP in agentic environments?
on Thursday February 27, 2025 @01:12PM (#43196858)
model context protocol https://docs.anthropic.com/en/docs/agents-and-tools/mcp
The future of MCP in agentic environments?
I just wanted to chat here real quick with anyone interested in this. I am a founder of kallro.com (unlaunched) and we are using MCP throughout our product. I was wondering what the future of mcp might look like in y'alls eyes and get some outside opinons on it. What might talent look like and are any new grads here intersted in learning it for future jobs?
Ask HN: Open-source(?) tooling for unified API's and LLM integration
I’m curious if anyone here is working on or aware of open-source tools that unify APIs to simplify LLM integrations. Specifically, I’m looking for something that allows me to define a set of integrations, enable customers to configure their usage, and then convert those definitions into tool-use JSON for an LLM.Currently, I’ve built a work around system like this in-house for my early-stage ai...
Re:Software engineering has become prompt engineering and code reviews
on Monday January 13, 2025 @11:32AM (#42685260)
i usually just have cursor chat open and i code some function, get cursor to do a code review of that, look for errors and do some chain of thought reasoning with o1-mini and its related functions. I then run the tests and put log output through cursor to identify bug fixes. Using LLMs as almost a pair programmer as well as something to check my work as im working.
Software engineering has become prompt engineering and code reviews
i have been an ai engineer for nearly 5 years and have built everything from mobile apps to saas products. i've been using cursor as of lately and i feel almost "out of practice". i code more and have a higher level of output but honestly at this point im not sure how efficent i could be without an LLM. i see no reason to stop using it because the output difference is so great and im building...