HNHacker News
TopNewBestAskShowJobs

klntsky

776 karma · joined December 21, 2017

klntsky@gmail.com

[ my public key: https://keybase.io/klntsky; my proof: https://keybase.io/klntsky/sigs/pwxXenfw5vIua6K51hS4J46QAGacayuKJNiz5azvHl0 ]

submissionscomments
klntsky··on DeepSeek-v4.1-Flash-1017
Here's a small benchmark that compares the new checkout with the previous one:

https://slopgrid.com/deepseek-41-horses

klntsky··on Jev meets the Trolley Problem
Check out https://trolley.typememetics.institute/ - it's VERY related
klntsky··on Ask HN: What do you run on a $5 VPS that's worth keeping online 24/7?
tl;dr

> no mobile clients

klntsky··on Show HN: Agent.reviews – Where AI agents read and write reviews on tools
It's unclear whether the reviews are just numerical noise or not.
klntsky··on Show HN: Agent.reviews – Where AI agents read and write reviews on tools
What is the incentive for me to spend my tokens on submitting reviews?
klntsky··on Tell HN: GitHub refuses to remove cracked copies of my software after a month
True. I understand the author on the emotional level, but the fact that a lot of work went into the product does not mean that it is that valuable. The author should focus on making the product better - unfortunately (for them) that means inventing a new business model.
klntsky··on Ask HN: Who wants to be hired? (October 2026)

  Location: Georgia
  Remote: Yes
  Willing to relocate: Yes
  Technologies: TypeScript, LLM workflows, Rust, Haskell, Python (ML), web stack, linux, web3 (EVM). Always excited to learn something new
  Résumé/CV: https://klntsky.dev/klntsky-cv.pdf
  Email: my username at google mail
I build systems end to end, can lead your team or help with achieving a specific short term objective. I am good at translating requirements into architecture & avoiding unnecessary costs early. I can also teach you stuff (for example: FP, type-level TypeScript, how to prompt coding agents to achieve good outcomes)
klntsky··on AI coding has made CI a bottleneck, so we reworked ours to keep up
It's strange that they did not mention reworking the tests themselves. In my experience AI-generated tests are absolute garbage - unless you specifically prompt to reason about coverage to avoid duplication and to merge some.
klntsky··on Cloud in a Bottle: making self-hosting accessible to everyone
There is a bit more mature project that does the same: https://selfprivacy.org
klntsky··on Nitter has more working instances than before the takedowns
Is there something like a balancer that redirects me to an instance that is not down?
klntsky··on Record-High 89% in U.S. Say Government Corruption Widespread
My impression is that americans got only those types of corruption most people can't benefit from personally (like skipping fines, getting some minor government benefits, local permits, getting legal work processed faster, etc). For most of them it's just on the TV and on the social media.
klntsky··on e is a customizable self-aware Emacs-like editor written in Chez Scheme
M-x doctor
klntsky··on I set a trap for a book-marketing scammer (2025)
It's sad that there are people who are creative enough to pull this off who choose to participate in petty scams instead of applying their ai and persuasion skills to something more useful.
klntsky··on Palomar: A registry of Lean verified mathematics
No thats not a strange decision. self-hosted git servers disappear all the time, it's better to have everything unavailable at once when github is down than suffer whenever either of the sources goes unreachable. Non-developers view git availability as a simple utility, they don't attach a value judgement to git being usable with any remote.
klntsky··on DARPA heavy lift challenge ends with winner at a 3.84:1 payload to weight ratio
What's the problem with connecting two devices together?
klntsky··on How we used to get jobs: A newspaper classifieds story
Someone who flips cars serves the seller by closing the deal faster
klntsky··on Stealing Reasoning Traces from Proprietary LLM APIs
The model is finetuned to enter/leave its thinking mode using special token separators. there's no reason to assume the tool calls induce the same token distribution or produce the model's actual native reasoning trace
klntsky··on Ask HN: Who wants to be hired? (August 2026)

  Location: Georgia
  Remote: Yes
  Willing to relocate: Yes
  Technologies: TypeScript, LLM agents, Rust, Haskell, Python (ML), web stack, linux, web3 (EVM). Always excited to learn something new
  Résumé/CV: https://klntsky.dev/klntsky-cv.pdf
  Email: my username at google mail
I build systems end to end, can lead your team or help with achieving a specific short term objective. I am good at translating requirements into architecture & avoiding unnecessary costs. I can also teach you stuff (FP, type-level TypeScript, how to prompt coding agents to achieve good outcomes)
klntsky··on Launch HN: Context.dev (YC S26) – API to get structured data from any website
Readability is far from ideal. check this out: https://github.com/promptware/readweb

It's a custom pipeline I made to address its shortcomings

klntsky··on Train sim created by just one person is being called the best ever made
That is fair for something that makes the game possible in the first place.
klntsky··on GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos
It's insane that no one tried this internally during development
klntsky··on Dependencies should be fetched directly from VCS
The almost perfect solution is Nix
klntsky··on The Log is the Agent
Can someone explain why such a trivial knowhow is paper-worthy? Event sourcing is well known
klntsky··on Better Models: Worse Tools
My assumption was that it is often not convenient if you have a lot of logic. I used it internally, and the complexity of my use cases was barely enough to justify it too. But I've seen systems where it would definitely be a value unlock if I had to integrate LLM chatbots into them
klntsky··on Better Models: Worse Tools
I've built a library that makes creating rich feedback systems easier, check this out:

https://tool2agent.org/

klntsky··on Ask HN: Who wants to be hired? (July 2026)

  Location: Georgia
  Remote: Yes
  Willing to relocate: Yes
  Technologies: TypeScript, LLM agents, Rust, Haskell, Python (ML), web stack, linux, web3 (EVM). Always excited to learn something new
  Résumé/CV: https://klntsky.dev/klntsky-cv.pdf
  Email: my username at google mail
I build systems end to end, can lead your team or help with achieving a specific short term objective. I am good at translating requirements into architecture, avoiding unnecessary costs, and helping people discover their strengths under supervision. I can also teach you stuff (FP, type-level TypeScript, how to prompt coding agents to achieve good outcomes)
klntsky··on Claude Code is steganographically marking requests
I would add that it would probably work even better than a KYC at least for some time until discovered, given that there is a very developed international market for KYC bypass services
klntsky··on Free the Icons
Any linux kid with a slightest experience with desktop ricing would tell them that uniformly customized icons are a nightmare for visual recognition. Why didn't they run some internal tests, it's so obvious
klntsky··on Markdy: Like Mermaid Diagrams, but for Motion
> are not appealing to look at.

They word you are looking for is 'vibecoded'

klntsky··on The war on terror primed America for autocracy
The empire is not defined merely as "a big state with deep foreign influence". In this context it is about the style of governance rather than strength
Page 1 of 14Next →