ansonhw
Re:Ask HN: Anyone Building an AI Airtable?
on Wednesday October 08, 2025 @03:03PM (#45519456)
chatsheet.com
no embeddings yet, but soon
Re:Neoq – a queue-agnostic background job library for Go
on Sunday June 01, 2025 @05:28AM (#44149666)
Ya this is nice that it’s infra agnostic instead of requiring tons of dependencies.
Re:Ask HN: Is Slack Down?
on Monday May 12, 2025 @07:17PM (#43968345)
down again for me
Re:Ask HN: Is Slack Down?
on Monday May 12, 2025 @06:36PM (#43968101)
not sure why i didn't see any status updates
Re:Ask HN: Is Slack Down?
on Monday May 12, 2025 @06:35PM (#43968099)
was down (messages not going through) for me, then web was ok, then all went down, now back up
Re:Modal SDKs for JavaScript and Go
on Wednesday April 30, 2025 @02:12PM (#43848869)
excited for this to run sandboxes
Re:Why is there no RAG based file manager app in the market so far?
on Monday April 07, 2025 @02:34PM (#43614501)
we're working on this at chatsheet.com
what features are you looking for?
Re:The Next $100B+ Company Will Be for Non-Technical Users–and How It ...
on Wednesday March 19, 2025 @12:52PM (#43414435)
Agree that's what we're trying to do at chatsheet.com
Program in "plain english" but as powerful as writing code
Re:Ask HN: In what ways has AI tools have replaced your old way of doi...
on Tuesday March 04, 2025 @03:08AM (#43251743)
i stopped manually updating airtable and excel. all doc/web/pdf flows auto update.
Re:Majority of workers (55%) rarely or never use AI chatbots at work
on Wednesday February 26, 2025 @04:20AM (#43182142)
Doesn't this mean 45% of workers already do use AI chatbots? Glass half full vs empty
Re:Save Worker 17
on Wednesday February 26, 2025 @03:00AM (#43181704)
Save Worker 17 o7
Re:Learning AI? The Real Hurdle Isn't Complexity, It's Jargon
on Sunday February 23, 2025 @07:51AM (#43148909)
tech world: rag, llm, prompting, agents, bla bla
normies: chatgpt
Re:Ask HN: Why Isn't Anyone Building a Global Brain for LLMs?
on Friday February 07, 2025 @10:46AM (#42973980)
Hmm i'll check out the pagerank stuff, IMO RAG isn't super great. I think RAG overall has been oversold since embeddings KNN hasn't proven to be super accurate.
Re:From Python to Go
on Friday February 07, 2025 @10:19AM (#42973634)
Go is the best for scale out, concurrent agents
Re:PDFxtract – Automate Data Extraction from PDFs with AI
on Friday February 07, 2025 @02:47AM (#42970423)
Gemini
Re:Ask HN: Why Isn't Anyone Building a Global Brain for LLMs?
on Friday February 07, 2025 @02:09AM (#42970231)
Hmm i think the issue with any large data set is indexing + querying. At https://usefind.ai/ this is a fundamental problem we've been trying to tackle. What kind of structure do you think would work?
Re:Ask HN: Why Isn't Anyone Building a Global Brain for LLMs?
on Thursday February 06, 2025 @01:58PM (#42965355)
I'm confused why search + LLM wouldn't work for this?
Re:Spanish ministers agree to cut legal working week to 37.5 hours
on Wednesday February 05, 2025 @12:16PM (#42951806)
NGMI
Re:Chat is a bad UI pattern for development tools
on Tuesday February 04, 2025 @02:31PM (#42937401)
I agree actually that chat is overrated overall as UX. It works really well for chatgpt but creates the wrong ux expectations for users where more precision or constraint is needed. Also not good for large processing. It was magic though for chatgpt.
Re:Show HN: Airweave – Turn App Data into Agent Knowledge
on Tuesday February 04, 2025 @02:30PM (#42937378)
Does it support pgvector over weaviate?
Re:Microsoft Paint is getting a Copilot button
on Monday February 03, 2025 @12:20PM (#42920506)
why is bill gates so obsessed with bringing back clippy
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
on Monday January 27, 2025 @04:57AM (#42839278)
Check the screenshot below re: training on OpenAI Outputs. They've fixed this since btw, but it's pretty obvious they used OpenAI outputs to train. I mean all the Open AI "mini" models are trained the same way. Hot take but feels like the AI labs are gonna gatekeep more models and outputs going forward.
Re:Introducing Operator
on Saturday January 25, 2025 @12:46AM (#42819784)
Feedback -> paying Scale AI to babysit/label tons of these sessions.
It will just be like the post training that turned GPT3 into the original ChatGPT.
Re:Introducing Operator
on Friday January 24, 2025 @01:29AM (#42810979)
When:
1/ More accurate + less supervision
2/ Faster
3/ Background + Parallel
Will be the magic moment. Currently like supervising a grandparent using the web. But there's huge potential if ^^^ happens. Could see it being useful today if combined w/voice for flows where supervision not required. Example: asking w/voice to make reservations while driving.
Re:Launch HN: Innate (YC F24) – Home robots as easy to program as AI a...
on Wednesday December 18, 2024 @05:46PM (#42456341)
sick
Re:Ask HN: How are LLM's served at scale?
on Sunday December 15, 2024 @07:41AM (#42423123)
good batching and tensor parallelization prob
Re:Ask HN: Is the Golang ecosystem health declining?
on Friday December 13, 2024 @11:10AM (#42409822)
Hope not - we just rewrote our entire stack w Go . We're massive fans of it.
Re:Find AI v3 – Perplexity Meets LinkedIn (1B+ Profiles) + New API
on Friday November 29, 2024 @12:35PM (#42275458)
Earlier this year, we launched Find AI v1:https://news.ycombinator.com/item?id=40801494. It was a tool for searching LinkedIn-style data with natural language queries. It worked well for tech-focused searches, but the dataset was small and queries were limited.
With v3 (yes a 2 version improvement), we’ve overhauled everything. Our new algorithm uses deep research agents combining multiple data sources and can search over 1B+ profiles (more than LinkedIn). The new version also handles more nuanced searches, like:
- For selling GPU Cloud services: “Companies that have done a Series A hiring for Pytorch”
- For SDR’s: "AI companies that raised $20M+ Series A."
- For VC Partners: "Ex-OpenAI employees founding 'stealth' startups."
- For IR Professionals: "Head of alternatives investing at large private wealth firms."
- For Recruiters: "Fullstack engineers experienced with Go and Svelte."
We deleted all our old code (Ruby on Rails) and rebuilt the entire stack with Go + Svelte 5 (which we love) for speed and scalability. It’s now 10x faster, with a new UI and features like threaded searches.
We’re also launching an API, so you can integrate Find AI into your own apps. The API has also launched as an integration in Clay—learn more here: https://www.clay.com/university/lesson/find-ai-integration-o....
We started building Find AI to help founders, recruiters, and investors find the right people faster. Try it out here: https://usefind.ai/.
Would love your feedback and questions!
Spare H100 HGX’s Available to Rent
Our company is an AI studio that ordered HGX’s to host for model training and we have some spare capacity available. They’ll be racked and ready in ~10-15 days, [TBC we aren’t a hosting business so these will be raw nodes with SSH access, no software, K8s, etc pre-installed]. We’re renting them on a 3-year contract basis, first-come, first-served. If interested, please email or comment...