lfx
Re:OpenClaw 2.0, Accidentally
on Monday August 31, 2026 @12:41PM (#49511781)
Thats cool, did not know that, thanks!
What about pi?
Re:OpenClaw 2.0, Accidentally
on Monday August 31, 2026 @12:12PM (#49511453)
Is this something native by pi, or from 3rd party devs?
Re:Show HN: Mole – Deep research agent for your terminal
on Friday August 14, 2026 @04:26PM (#49304140)
DataMole?
ResearchRat?
DRR? (Deep Research Rat)?
Re:How I use LLMs to learn complex topics
on Sunday August 09, 2026 @09:05PM (#49238078)
Newcomers have to do exactly the same what they did years and years ago. Practice the craft and gain experience by doing things.
And the craft is loose term, it can mean anything you like to get better at.
Re:How I use LLMs to learn complex topics
on Sunday August 09, 2026 @09:01PM (#49238045)
Author likes this kind of animation. I have something similar like this, but without the animation step.
The main idea is you can do any style you want or like to learn.
Re:Agent Skill to Force Docs in ASD-STE100 Simplified Technical English
on Thursday July 30, 2026 @11:00PM (#49118513)
Flight fire with fire!
Re:Ask HN: Do you see a Pancake in the top left menu at Github.com?
on Thursday July 30, 2026 @01:54PM (#49113355)
Why so much hate.
I think this is brilliant way to announce new features!
It is playful, it is nice, it is something new. Don't take it too seriously.
Re:Show HN: Whetuu – a zero-config cross-shell prompt written in Zig
on Thursday July 23, 2026 @12:44PM (#49024567)
This is awesome -
*A history picker on the up arrow*
*Commands are recorded once they finish, and only when they exited cleanly, so typos never clutter the list.*
Where the history is stored? Is it possible to store in single place like user root dir?*
Re:VulnHunter: Capital One's agentic AI code security tool
on Friday July 17, 2026 @01:53PM (#48950202)
There are few more:
https://github.com/visa/visa-vulnerability-agentic-harness
https://github.com/cloudflare/security-audit-skill
I'm on the fence here, for one as from recent Linux mailing discussions those tools can really find good bugs (51% of them?), but on other side - I'm afraid of false sense of security.
Re:Kimi K3 is now live
on Thursday July 16, 2026 @12:06PM (#48936435)
You need a friend there. I'm trying to get in for years, however RO mode is still worth it.
Re:Kimi K3 is now live
on Thursday July 16, 2026 @11:56AM (#48936281)
I saw it after posting. Ha. That is not very smart filter, but works most of the time!
Re:Kimi K3 is now live
on Thursday July 16, 2026 @11:09AM (#48935640)
Re:Vancouver PD website features Quick Escape button that wipes itself...
on Tuesday July 14, 2026 @10:28PM (#48915542)
Not all crimes are reported in Vancouver. But agree is not as bad as some paints.
Re:Opinionated and Easy Pi.dev Configuration
on Thursday July 09, 2026 @02:33PM (#48850467)
60+ ! oh my, while this is cool it seems that is overkill. I want to know all my skills back and forth.
But I like this kind of projects where I can peak of what extensions other people use. Is like .vimrc file back in the day. Do not clone blindly, but peak, learn and copy what is needed.
Re:A Practical Guide to SSH Tunnels: Local and Remote Port Forwarding
on Wednesday June 24, 2026 @12:11PM (#48662037)
It goes like this:
---
As an expert tutorial creator for experienced engineers, you take the input the user request and make interactive tutorial. Default style is technology, tech is mac and linux. Default style is 20mins, but you ask for the timeline. Also do not forget to provide the cost of technologies used.
---
Re:A Practical Guide to SSH Tunnels: Local and Remote Port Forwarding
on Wednesday June 24, 2026 @10:03AM (#48660038)
I do this all the time, I have a skill/gem with instructions on how I want to receive info, how to format and so on. Really helps to go fast to get the point.
Dbt Core v2 is here: still open source, now rebuilt for what's next
Re:Ruby for Good
on Sunday May 24, 2026 @01:06PM (#48259048)
I understand why rust, but why TS? just for a front end?
Re:Railway Is Having a Major Outage
on Tuesday May 19, 2026 @09:04PM (#48201773)
That’s true, however having only few eggs and shopping for several baskets does not make sense in early days. Not sure how big railway is, but usually you start small with one egg.
Re:Parallel Agents in Zed
on Wednesday April 22, 2026 @03:04PM (#47867852)
I loved zed for over 1 year, told for everybody to use it, because it was so fast and great.
But now using claude-code,gemini-cli,codex,etc it just seems less relevant. Just opened nvim with lazyvim and it feels nice, since I'm in terminal anyway it just feels more natural.
Still have zed opened, still like it but I guess honeymoon is over.
Addy Osmani, Death of the IDE?
Re:Show HN: I Was Here – Draw on street view, others can find your dra...
on Tuesday March 10, 2026 @09:24AM (#47322946)
Cool idea, but you should consider required auth to ban trolls.
On other hand, I wonder why many pictures are in the middle of the bridges or viaducts?
Re:Claude Code for Infrastructure
on Friday February 06, 2026 @04:04PM (#46918110)
Peak in my profile.
Re:Claude Code for Infrastructure
on Wednesday February 04, 2026 @02:50PM (#46890702)
Hey Collin!
Interesting idea, few things:
- The website tells less than your comment here. I want to try but have no idea how destructive it can be.
- You need to add / mention how to do things in the RO mode only.
- Always explain destructive actions.
Few weeks ago I had to debug K8S on the GCP GDC metal, Claude Code helped me tons, but... I had to recreate whole cluster next day because agent ran too fast deleted things it should not delete or at least tell me the full impact. So some harness would be nice.
Re:Ask HN: Could you share your personal website here?
on Wednesday January 14, 2026 @04:49PM (#46624120)
https://blog.cloudbear.dev/
Simple blog, planning to expand a lot this year (as every year).
Re:Gemini 3 for developers: New reasoning, agentic capabilities
on Tuesday November 18, 2025 @11:59AM (#45968913)
Technically you can!
I haven't seen it in the box yet, and pricing is unknown https://cloud.google.com/blog/products/ai-machine-learning/r...
Re:Gemini 3 for developers: New reasoning, agentic capabilities
on Tuesday November 18, 2025 @11:58AM (#45968893)
Just hand sketched what 5 year old would do on the paper - the house, trees, sun. And asked to generate 3d model with tree.js.
Results are amazing! 2.5 and 3 seems way way head.
Re:Honda: 2 years of ml vs 1 month of prompting - heres what we learned
on Friday November 14, 2025 @04:47PM (#45932573)
It really puzzles me how this is helping and how it was done?
Does it make text more clear? How exactly? Does the German language is more descriptive? Does it somehow expands context?
So many questions in this fun fact.