HackerTrans
TopNewTrendsCommentsPastAskShowJobs

echollama

no profile record

Submissions

[untitled]

1 points·by echollama·8 माह पहले·0 comments

[untitled]

1 points·by echollama·9 माह पहले·0 comments

[untitled]

1 points·by echollama·9 माह पहले·0 comments

Engineered Addictions

masonyarbrough.substack.com
720 points·by echollama·पिछला वर्ष·451 comments

The Incentive Structure That Makes Social Media Addiction Inevitable

masonyarbrough.substack.com
2 points·by echollama·पिछला वर्ष·0 comments

Show HN: Ask-human-mcp – zero-config human-in-loop hatch to stop hallucinations

masonyarbrough.com
129 points·by echollama·पिछला वर्ष·61 comments

The future of MCP in agentic environments?

6 points·by echollama·पिछला वर्ष·3 comments

[untitled]

1 points·by echollama·पिछला वर्ष·0 comments

Ask HN: Open-source(?) tooling for unified API's and LLM integration

1 points·by echollama·पिछला वर्ष·1 comments

Software engineering has become prompt engineering and code reviews

2 points·by echollama·पिछला वर्ष·4 comments

comments

echollama
·पिछला वर्ष·discuss
agreed its like saying that jerking off makes you healthier
echollama
·पिछला वर्ष·discuss
i fixed this
echollama
·पिछला वर्ष·discuss
yes it is
echollama
·पिछला वर्ष·discuss
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.
echollama
·पिछला वर्ष·discuss
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.
echollama
·पिछला वर्ष·discuss
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.
echollama
·पिछला वर्ष·discuss
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.
echollama
·पिछला वर्ष·discuss
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.
echollama
·पिछला वर्ष·discuss
model context protocol https://docs.anthropic.com/en/docs/agents-and-tools/mcp
echollama
·पिछला वर्ष·discuss
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.