HackerTrans
TopNewTrendsCommentsPastAskShowJobs

saran945

no profile record

Submissions

Fugu: Learn to assemble, route, and coordinate expert agents [pdf]

github.com
3 points·by saran945·23 giorni fa·0 comments

Turn any software into an agent-native CLI

github.com
2 points·by saran945·4 mesi fa·1 comments

Show HN: API to get structured data from any site's search

searchresult.dev
2 points·by saran945·5 mesi fa·0 comments

Show HN: Convert Anything, Instantly

toolbox.run
3 points·by saran945·7 mesi fa·2 comments

Algorithms are jailed in PDF files

2 points·by saran945·10 mesi fa·0 comments

Automating IDEs: Who's Working on It?

2 points·by saran945·anno scorso·0 comments

Show HN: AI Feed

weblist.ai
1 points·by saran945·2 anni fa·0 comments

Future of Online Tasks

1 points·by saran945·2 anni fa·0 comments

Show HN: Generate and follow Structured Feeds from any web page

weblist.ai
3 points·by saran945·2 anni fa·0 comments

Commit0: Library Generation from Scratch

openreview.net
2 points·by saran945·2 anni fa·0 comments

Show HN: Monitor Any List Page Without RSS Feeds

weblist.ai
2 points·by saran945·2 anni fa·1 comments

Single prompt achieves competitive results with o1-preview

arxiv.org
3 points·by saran945·2 anni fa·1 comments

An agent to navigate previously unseen code repositories to solve queries

github.com
1 points·by saran945·2 anni fa·0 comments

Show HN: I made a tool to receive alerts when answers change

alertfor.com
157 points·by saran945·2 anni fa·81 comments

Show HN: Long query, slow and continuous search –> alerts

alertfor.com
3 points·by saran945·2 anni fa·0 comments

APPL: A Prompt Programming Language

appl-team.github.io
2 points·by saran945·2 anni fa·1 comments

Reasoning model on par with GPT3.5 turbo

github.com
2 points·by saran945·2 anni fa·0 comments

AutoDev: Automated AI-driven development by Microsoft

arxiv.org
163 points·by saran945·2 anni fa·213 comments

comments

saran945
·4 mesi fa·discuss
CLI-Anything generates a complete command-line interface for existing software (if codebase available). they've already generated CLIs for 11 complex applications, I guess this is cool, can be used to make classic software to Agentic enabled. .
saran945
·7 mesi fa·discuss
currencies are hard code as of now, Will connect with some api's.

"100 watt hours to joules", Thanks for let me know - its a parsing error.
saran945
·anno scorso·discuss
“The AMT/AIT was also weaponized by certain political elements in India to proliferate harassment against the Brahmins of Tamil Nadu”

I was born and raised in Tamil Nadu, having lived there for over two decades. In my experience, I have not witnessed any widespread harassment specifically targeting Brahmins. While isolated incidents may exist—just as they do for various communities across all states—there is no substantial evidence to suggest a systemic issue. Could you provide concrete examples, statistics, or credible sources to substantiate this claim ?
saran945
·2 anni fa·discuss
Extracting a list page using an LLM costs $1, so I reused the selectors when extracting data from the same page in subsequent operations to optimize costs. the extraction works well for search result pages as well. As far I know none of the websites provide as an RSS feed for search results.
saran945
·2 anni fa·discuss
I have downloaded exe for windows, Chrome saying "Failed virus detected"
saran945
·2 anni fa·discuss
"We evaluated REAP using a dataset designed to highlight the limitations of large language models (LLMs), comparing zero-shot prompting with REAP-enhanced prompts across six state-of-the-art models: OpenAI’s o1-preview, o1-mini, GPT-4o, GPT-4o-mini, Google’s Gemini 1.5 Pro, and Claude 3.5 Sonnet. The results show significant performance improvements, with o1-mini increasing by 40.97%, GPT-4o by 66.26%, and GPT-4o-mini by 112.93%. While OpenAI's o1-preview already demonstrated strong baseline performance, it still showed modest gains. In addition to the performance improvements, REAP provides a cost-effective solution. For instance, GPT-4o-mini, which is about 100 times cheaper than o1-preview, delivered competitive results."
saran945
·2 anni fa·discuss
Cool.

1. Currently, it's a proof of concept only. In the next release, I will make sure to include some use cases/examples.

2. I haven’t finalized the pricing yet. For now, it's free. When I release, the starting price will be around $7-10 per ~200 runs/questions. I’m also considering offering a free tier; I’ll work that out later. Thank you.
saran945
·2 anni fa·discuss
I made using https://www.screen.studio/
saran945
·2 anni fa·discuss
Extended version Autogen. Added 8 new tools and modified some prompts. I never expected this much quality. linking my tiny benchmarking test in a tweet. https://x.com/saran945/status/1815441284812738734
saran945
·2 anni fa·discuss
I don't understand your question. . .

Do you need more details about How it finds the answer? I already shared most of the part in this thread.

The home page was done in 60 minutes, the whole product was done in 3 days. I was testing and releasing without any intention.
saran945
·2 anni fa·discuss
I slept, sorry for the delay reply.

The quality of LLM does not improve my product much, I am facing extraction issues, will have to improve continually.

"You are going to see a lot of competition in this space." I welcome them all :)
saran945
·2 anni fa·discuss
Huginn is a great product, though I never used, I am aware of the value it provides. Alertfor is not similar to Huginn. my product is part of something else, I extracted and unleased as separate product. Will go in different direction.
saran945
·2 anni fa·discuss
The rules suggesting that I would get more feedback if there is no signups. Anyways, luckily I have got enough feedback :) next release will have some public access without signups.
saran945
·2 anni fa·discuss
sure. I do not stop.

I have designed the product for consumers and professionals. Since it's a new kind of product (?), I'm unsure what to call it. The agents continuously search the web on behalf of the user and create a feed for each query. Let me think more . . .
saran945
·2 anni fa·discuss
RAG is to enhance the generation capabilities of a language model by integrating external knowledge sources (DB, KB etc). This is done by retrieving relevant information from a knowledge base or document store and using it to inform or augment the model's responses.

Langchain is a library specifically designed to facilitate the development of applications using LLMs. It provides tools and utilities to build complex NLP pipelines with ease.

Alertfor is a SaaS product that combines LLMs with agents to provide automated search.

Does this answer your question ?
saran945
·2 anni fa·discuss
Awesome!!

Kindly try now with same question. I made some changes. I use Bing API as a initial resource selector. there were some issues. fixed it.
saran945
·2 anni fa·discuss
I use LLM+Agentic framework, it runs every 6 hours. In the next release I will provide UI to customize it (daily, weekly, 6 hours).
saran945
·2 anni fa·discuss
This is a best advice, repeatedly hearing it.

focus on a promising niche that has a problem and is willing to spend money on it is often regarded as best practice. many successful companies have been built on this principle. Unfortunately, this approach has never worked for me. I have worked on many products and followed these best practices, but I have yet to see success. Over the past 12+ years, I have experimented these best practices but nothing has worked. It would work for founders who has good networking /connections, living in CA, best in marketing, have good followers in Social media etc. Founder like me have no such assets. this is a big chicken or egg problem.

Instead, I decided to take a different approach and I create imaginative products based on ideas I'm passionate about and publish them continuously. If there is an interest, I then optimize the product for the interested customers, taking their feedback into account and continuing development accordingly.
saran945
·2 anni fa·discuss
Please bear with me, Its not showing on mobile.

https://vimeo.com/991338343
saran945
·2 anni fa·discuss
It's a surprise to see weekly queries. If you don't mind, could you please share one or two examples of these queries?

I've added all suggestions from entire thread to my log and will prioritize implementing them.

Regarding pricing, I don't know offering a free tier is right approach or not .. I believe that the queries are complex and long. not sure they could be shared among users. Anyways, for next 2 or 3 months its going to be beta. my current focus is adding value, will ask the users about pricing later. Note that, for each question, it crawls 10-15 pages, or even more if you ask to enrich a table. there is LLM cost, now a days webpages are really huge.

Thank you again for your input and support. Please let me know if you have any other thoughts or questions.