stan_kirdey
Re:Show HN: Clark code – open-source IDE for OSS coding and free tier
on Thursday August 06, 2026 @03:22AM (#49193574)
* can be controlled from android phone
* free tier is deepseek flash lite
* GLM 5.2 + Kimi K3
* comes with extra freebies like Clark web agent
Re:Discovery Loop
on Thursday August 06, 2026 @12:45AM (#49192564)
*self-discovery loop more like it :-)
Re:Clark Code
on Thursday August 06, 2026 @12:30AM (#49192453)
hey folks, been building clark code - somewhat better version of codex optimized for OSS models, it now has fully free tier with deepseek flash lite behind it. Been a great daily driver for a ton of coding, and a lot of clark code is built with clark code - rust, tauri, low memory profile, and you can prompt it and manage sessions from android phone remotely (love this in codex)
I know it is a bit of promo, but also I think free tier is really great value, so wanted to share it here.
Features I love:
* agentic loop is lean based on https://github.com/clark-labs-inc/clark-agent
* has "manus" style wide internet research capability if it is needed for coding project
* free
* works locally on laptop or has a daemon to work over ssh on another host
* prompts are heavily optimizied for correct autoregressive generation
* strong eval system for all features so all models behaves very predictiably
* windows, linux and mac supported (windows unsigned, still waiting on msft ................ )
* comes with quite nice, manus stile cloud agent called clark (also has free tier, but diff model)
Clark code now working on better motion animation system of itself as I am typing it :-) Check it out - www.clarkchat.com/clark-code - if anything, another tool in the toolbox when codex limits are not reset by Tibo!
Clark Code
Show HN: Clark – AI assistant with own computer
Hey folks, I've been building Clark solo, with the aim to match Manus agent (I really like it!) in features and capabilities, but also in its relentless ability to just complete tasks while using browser, computer etc. So far I think I've achieved 1:1 core feature parity: 1) computer use agent 2) browser use in same thread 3) wide and deep research - clark calls clark 4) integration with google...
Show HN: Clark Hash, 32x smaller searchable sketches for embeddings
https://github.com/clark-labs-inc/clark-hash
made a small library using GPT5.5-Pro and autoresearchyou can convert 384-dim f32 vectors go from 1536 bytes to 48 bytes without calibration. works for petabyte scale processing of text in pure online manner.
Show HN: Clark-agent, a Rust library for LLM tool loops
https://github.com/clark-labs-inc/clark-agent
Hi HN,I wrote clark-agent, a small Rust library for running LLM tool loops.The loop is:context -> model -> tool call -> tool result -> repeatThe parts I wanted typed were:- transcript messages - tool calls - tool results - stream events - tool schemasThe model/provider boundary is a StreamFn trait. Tools implement AgentTool. There are hooks for things like context transforms, tool...
Re:Show HN: Clark-Browser – Stealth Chromium
on Wednesday May 20, 2026 @03:33AM (#48204355)
Just ran evals on a few detectors, and clark-browser passed live stealth checks on Cloudflare smoke, SannySoft, BrowserLeaks Client Hints, and WebGL.
Results + new binary https://github.com/clark-labs-inc/clark-browser
Re:Gemini 3.5 Flash
on Tuesday May 19, 2026 @03:24PM (#48198155)
EXPENSIVE ._.
Show HN: LibreOffice-rs – I built a pure-Rust LibreOffice using autoresearch
https://github.com/clark-labs-inc/libreoffice-rs
Hey HN,I built libreoffice-rs: a pure-Rust, std-only library + CLI for reading, writing, converting, and rendering office documents — with *zero* LibreOffice, Java, or C dependencies.100x faster... I know, I know.It supports DOCX, XLSX, PPTX, ODT/ODS/ODP, PDF, Markdown, CSV, HTML, SVG, and more. The CLI is designed to feel familiar:```bash cargo install libreoffice-pure# soffice-style...
Re:Show HN: Clark-Browser – Stealth Chromium
on Tuesday May 19, 2026 @02:10AM (#48189816)
clark-browser is c++ level overwrite of core chromium parts
Show HN: Clark-Browser – Stealth Chromium
https://github.com/clark-labs-inc/clark-browser
Fully open-sourced, perfect for agentic browsing, works with Vercel's agent-browser and playwright.
Re:I Cancelled Claude: Token Issues, Declining Quality, and Poor Support
on Friday April 24, 2026 @01:41PM (#47893458)
I also cancelled my subscription.The $20 Pro plan has become completely unusable for any real work. What is especially frustrating is that Claude Chat and Claude Code now share the exact same usage limits — it makes zero sense from a product standpoint when the workflows are so different. Even the $200 Max plan got heavily nerfed. What used to easily last me a full week (or more) of solid daily use now burns out in just a few days. Combined with the quality drop and unpredictable token consumption, it simply stopped being worth it.
LinkedIn – 500 Internal Server Error
claudeflare is down, vibe updates?
DeepSeek-v3.2
Re:Fara-7B by Microsoft: An agentic small language model designed for ...
on Wednesday November 26, 2025 @05:59PM (#46063283)
* fine tuned Qwen-7B
That could totally power next generation of green-screen techs. Generative actors may not find favorable response in the audiences; but SFX, decor, extras, environments that react to actors' actions - amazing potential.
Re:Enough AI Copilots, We Need AI HUDs
on Sunday July 27, 2025 @10:17PM (#44706586)
needed to find a kids’ orthodontist. made a tiny voice agent: feed it numbers, it calls, asks about price/availability/insurance, logs the gist.
it kind of worked. the magic was the smallest UI around it:
- timeline of dials + retries
- "call me back" flags
- when it tried, who picked up
- short summaries with links to the raw transcript
once i could see the behavior, it stopped feeling spooky and started feeling useful.
so yeah, copilots are cool, but i want HUDs: quiet most of the time, glanceable, easy to interrupt, receipts for every action.
Re:Disabling telemetry in ByteDance's VSCode fork increases data sent ...
on Sunday July 27, 2025 @06:58PM (#44705479)
props to OP for the screenshots and payloads—that’s how you do it. If any IDE wants trust, they know the recipe - make telemetry optin by default and provide a real kill switch.
Re:Windsurf employee #2: I was given a payout of only 1% what my share...
on Friday July 25, 2025 @03:54PM (#44687627)
Engineers: always negotiate for higher base salaries. In the vast majority of cases—especially during acquihires—your equity will be worth little or nothing. Founders and VCs still get paid; employees rarely do.
Don't just accept promises. Ask for the 409A valuation, liquidation preferences, and pay bands. If a company won’t provide transparency, that’s your signal.
Equity is a lottery ticket. Salary is money in the bank.
Re:Cozy video games can quell stress and anxiety
on Saturday April 19, 2025 @04:26AM (#43735044)
exactly for this made vortle.com
no login, no internet needed, no data collected, no score - just you and the game to de-stress and calm down
Show HN: Jslon – high performance GUI viewer of large JSONL, TSV and CSV files
For most tasks, GPT-4o/o3-mini are already great, and cheaper.
What is the real-world use case where GPT-4.5? Anyone actually seeing a game-changing difference? Please share your prompts!
Re:1561 Celestial Phenomenon over Nuremberg
on Sunday February 23, 2025 @12:22AM (#43146836)
i've asked sora to visualize the description as is from the wiki
https://sora.com/g/gen_01jmrkxzdsfnw94f0y2jvcerc6
Re:Show HN: Transform Your Codebase into a Single Markdown Doc for Fee...
on Friday February 14, 2025 @01:44PM (#43051631)
Nice! Built something similar in Rust that supports local and remote repos: https://crates.io/crates/r2md
Show HN: R2md – quickly export entire codebase to a single Markdown/pdf
super simple tool, what sets it apart is straight forward cli interface without too much noise
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
on Tuesday January 28, 2025 @10:01PM (#42861003)
made this super easy to use tool https://github.com/skirdey-inflection/r2md
Re:DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
on Sunday January 26, 2025 @04:29AM (#42828970)
I've been comparing R1 to O1 and O1-pro, mostly in coding, refactoring and understanding of open source code.
I can say that R1 is on par with O1. But not as deep and capable as O1-pro. R1 is also a lot more useful than Sonnete. I actually haven't used Sonnete in awhile.
R1 is also comparable to the Gemini Flash Thinking 2.0 model, but in coding I feel like R1 gives me code that works without too much tweaking.
I often give entire open-source project's codebase (or big part of code) to all of them and ask the same question - like add a plugin, or fix xyz, etc. O1-pro is still a clear and expensive winner. But if I were to choose the second best, I would say R1.
Re:Willow, Our Quantum Chip
on Monday December 09, 2024 @04:38PM (#42370804)
Is anyone fine-tuning llama to write Q#? I feel LLMs can be a helpful tool in learning how to code quantum systems.