Hacker News: klntsky

New comment by klntsky in "Bouncer: Block "crypto", "rage politics", and more from your X feed using AI"

klntsky — Sun, 12 Apr 2026 19:30:40 +0000

It should also click "see less often" on every detected bait post. Heals the algo really well if you do that persistently

New comment by klntsky in "Ask HN: Who wants to be hired? (April 2026)"

klntsky — Thu, 02 Apr 2026 03:30:48 +0000

  Location: Georgia
  Remote: Yes
  Willing to relocate: Yes
  Technologies: TypeScript, LLMs, Rust, Haskell, web stack, web3 (EVM)
  Résumé/CV: https://klntsky.dev/klntsky-cv.pdf
  Email: username at google mail

Looking for clients who need a technical leader SWE to bring their project to success.

I am good at simplifying things conceptually, translating requirements into structure, and enabling people under my supervision to develop their strengths.

New comment by klntsky in "Show HN: Gemini can now natively embed video, so I built sub-second video search"

klntsky — Tue, 24 Mar 2026 16:27:21 +0000

why not skip the text conversion? is it usable at all?

New comment by klntsky in "Mozilla to launch free built-in VPN in upcoming Firefox 149"

klntsky — Thu, 19 Mar 2026 06:13:26 +0000

Why are they trying to sell a VPN in the countries where users barely need it?

New comment by klntsky in "The dead Internet is not a theory anymore"

klntsky — Thu, 12 Mar 2026 10:17:23 +0000

It was too early. It even executed its crypto airdrop YEARS before it became a common form of distribution in web3

New comment by klntsky in "Ask HN: Who wants to be hired? (March 2026)"

klntsky — Tue, 03 Mar 2026 12:23:17 +0000

  Location: Tbilisi/Georgia
  Remote: Yes
  Willing to relocate: Yes
  Technologies: LLMs, TypeScript, Rust, Haskell, PureScript, EVM tooling
  Résumé/CV: https://klntsky.dev/klntsky-cv.pdf
  Email: my username at google's mail service

I'm mainly interested in solving problems around LLM/AI automation, FP, and DeFi.

New comment by klntsky in "Show HN: Respectify – A comment moderator that teaches people to argue better"

klntsky — Wed, 25 Feb 2026 23:01:14 +0000

How do you score toxicity? Do you have a list of criteria or just let the LLM hallucinate a number out of thin air?

New comment by klntsky in "Ask HN: Who wants to be hired? (January 2026)"

klntsky — Fri, 02 Jan 2026 21:39:59 +0000

  Location: Tbilisi/Georgia
  Remote: Yes
  Willing to relocate: Yes
  Technologies: TypeScript, Rust, Haskell, PureScript, LLMs, EVM tooling
  Résumé/CV: https://klntsky.dev/klntsky-cv.pdf
  Email: my username at google's mail service

I'm mainly interested in LLM/AI automation, FP, and DeFi.

New comment by klntsky in "Has the cost of building software dropped 90%?"

klntsky — Mon, 08 Dec 2025 22:05:11 +0000

People vibe one-off solutions for themselves all the time. They just don't have the desire to productionalize them. Frankly, product knowledge is something LLMs are not that good at

New comment by klntsky in "Leak confirms OpenAI is preparing ads on ChatGPT for public roll out"

klntsky — Sun, 30 Nov 2025 03:39:04 +0000

Opensource LLMs are absolutely not on par with gpt-5 for any agentic workflows

Tool2agent – build guardrails for LLM agents

klntsky — Sun, 16 Nov 2025 18:55:19 +0000

Article URL: https://github.com/tool2agent/tool2agent

Comments URL: https://news.ycombinator.com/item?id=45947422

Points: 2

# Comments: 0

New comment by klntsky in "Ask HN: What Are You Working On? (Nov 2025)"

klntsky — Mon, 10 Nov 2025 15:32:27 +0000

the 'start trial' button does not work.

New comment by klntsky in "Ask HN: What Are You Working On? (Nov 2025)"

klntsky — Mon, 10 Nov 2025 15:21:54 +0000

autofilled details are terribly wrong. even the name is that of another product

New comment by klntsky in "Ask HN: What Are You Working On? (Nov 2025)"

klntsky — Mon, 10 Nov 2025 15:14:57 +0000

You should probably make a version that is usable as an email filter plugin for mail servers

New comment by klntsky in "Ask HN: What Are You Working On? (Nov 2025)"

klntsky — Mon, 10 Nov 2025 15:07:29 +0000

search is a must here

New comment by klntsky in "Ask HN: What Are You Working On? (Nov 2025)"

klntsky — Mon, 10 Nov 2025 15:05:48 +0000

Hey, how can I contact you privately?

New comment by klntsky in "Ask HN: What Are You Working On? (Nov 2025)"

klntsky — Mon, 10 Nov 2025 14:48:00 +0000

https://tool2agent.org/ - guardrails for your AI agent implemented via tool call feedback

https://osint.moe/ - LLM-based app to build research graphs based on goal-directed web search

New comment by klntsky in "Tool2Agent – a protocol for LLM tool feedback workflows"

klntsky — Sat, 08 Nov 2025 11:56:41 +0000

This is a set of conventions and types that streamline some approaches I came up with while building LLM workflows.

LLM tool feedback systems are under-developed, and the reason for that is the lack of well defined interfaces.

tool2agent is a concrete set of such interfaces to build on top of.

Right now, AI SDK bindings are available.

If you are an LLM workflow developer, take a look at this example of a conversational chatbot:

https://github.com/tool2agent/tool2agent/blob/4cf340f77aa92e...

Here's a more detailed writeup: https://x.com/klntsky/status/1986816754241487251

Tool2Agent – a protocol for LLM tool feedback workflows

klntsky — Sat, 08 Nov 2025 11:56:41 +0000

Article URL: https://tool2agent.org/

Comments URL: https://news.ycombinator.com/item?id=45856048

Points: 1

# Comments: 1

New comment by klntsky in "A startup’s quest to store electricity in the ocean"

klntsky — Fri, 07 Nov 2025 10:00:07 +0000

> Sizable’s reservoirs could connect to any grid that’s near waters that are at least 500 meters (1,640 feet) deep.

How many big cities are there on earth with that depth available nearby?