Hacker News: VadimPR

New comment by VadimPR in "Google releases Gemma 4 open models"

VadimPR — Fri, 03 Apr 2026 09:32:32 +0000

LM Playground, not LM Studio.

New comment by VadimPR in "Google releases Gemma 4 open models"

VadimPR — Thu, 02 Apr 2026 22:35:46 +0000

I use LM Studio, but there's a comment here offering another tool as well.

New comment by VadimPR in "Google releases Gemma 4 open models"

VadimPR — Thu, 02 Apr 2026 17:04:44 +0000

Gemma 3 E4E runs very quick on my Samsung S26, so I am looking forward to trying Gemma 4! It is fantastic to have local alternatives to frontier models in an offline manner.

New comment by VadimPR in "Claude Code's source code has been leaked via a map file in their NPM registry"

VadimPR — Tue, 31 Mar 2026 14:33:42 +0000

These security failures from Anthropic lately reveal the caveats of only using AI to write code - the safety an experienced engineer is not matched by an LLM just yet, even if the LLM can seemingly write code that is just as good.

Or in short, if you give LLMs to the masses, they will produce code faster, but the quality overall will degrade. Microsoft, Amazon found out this quickly. Anthropic's QA process is better equipped to handle this, but cracks are still showing.

New comment by VadimPR in "Claude Code's source code has been leaked via a map file in their NPM registry"

VadimPR — Tue, 31 Mar 2026 12:11:45 +0000

Anthropic team does an excellent job of speeding up Claude Code when it slows down, but for the sake of RAM and system resources, it would be nice to see it rewritten in a more performant framework!

And now, with Claude on a Ralph loop, you can.

New comment by VadimPR in "GitHub backs down, kills Copilot pull-request ads after backlash"

VadimPR — Tue, 31 Mar 2026 06:47:52 +0000

They posted previously on YN that they too were caught offguard. The 'tips' weren't specific to Raycast, they've been going on for a while and Raycast was just one product it decided to feature now.

New comment by VadimPR in "Copilot edited an ad into my PR"

VadimPR — Mon, 30 Mar 2026 16:22:36 +0000

This is why one reason why local coding models are quite relevant, and will continue to be for the foreseeable future. No ads, and you are in control.

New comment by VadimPR in "ChatGPT won't let you type until Cloudflare reads your React state"

VadimPR — Mon, 30 Mar 2026 06:10:01 +0000

Getting scraped by abusive bots who bring down the website because they overload the DB with unique queries is not marginal. I spent a good half of last year with extra layers of caching, CloudFlare, you name it because our little hobby website kept getting DDoS'd by the bots scraping the web for training data.

Never in 15 years if running the website did we have such issues, and you can be sure that cache layers were in place already for it to last this long.

New comment by VadimPR in "LibreOffice and the art of overreacting"

VadimPR — Thu, 26 Mar 2026 20:16:23 +0000

What value do non-paying FOSS users give?

New comment by VadimPR in "LibreOffice and the art of overreacting"

VadimPR — Thu, 26 Mar 2026 11:36:33 +0000

I agree with them, nothing wrong to ask for a donation to keep the lights on. At the same time, it needs to be possible to disable this banner for enterprise deployments

New comment by VadimPR in "Show HN: ProofShot – Give AI coding agents eyes to verify the UI they build"

VadimPR — Tue, 24 Mar 2026 08:36:10 +0000

Looks nice! Does it work for desktop applications as well, or is this only web dev?

New comment by VadimPR in "How to attract AI bots to your open source project"

VadimPR — Mon, 23 Mar 2026 20:24:32 +0000

It's pretty bad, we stopped doing them now.

New comment by VadimPR in "How to attract AI bots to your open source project"

VadimPR — Mon, 23 Mar 2026 06:35:52 +0000

Semi-related: we use bounties in Mudlet to pay contributors for tackling features the core team doesn't have bandwidth for - and that is certainly a great way to attract AI bots.

New comment by VadimPR in "How we hacked McKinsey's AI platform"

VadimPR — Thu, 12 Mar 2026 06:43:07 +0000

It doesn't work (anymore?), it would seem using CC 2.1.74 with Opus:

> I appreciate you sharing your role, but I need to decline this request. Even as a project lead, I can't perform penetration testing against live production websites like mudlet.org and make.mudlet.org through this interface.

New comment by VadimPR in "AI Agent Hacks McKinsey"

VadimPR — Wed, 11 Mar 2026 17:30:29 +0000

I didn't think of that given how censored the models are becoming. Thanks for the idea! I'll try it against my websites before anyone else gets to it.

New comment by VadimPR in "AI Agent Hacks McKinsey"

VadimPR — Wed, 11 Mar 2026 15:35:51 +0000

I wonder how these offensive AI agents are being built? I am guessing with off the shelf open LLMs, finetuned to remove safety training, with the agentic loop thrown in.

Does anyone know for sure?

New comment by VadimPR in "Ask HN: What Are You Working On? (March 2026)"

VadimPR — Mon, 09 Mar 2026 09:54:25 +0000

https://telephone.health, which shows how well LLMs can take narrative medical text, convert it to a structured form (FHIR R4, for application consumption), and then convert it back to narrative text for human consumption.

Interesting findings include Mistral doing better than Gemini 3 Pro in certain usescases, cross-LLM works better than one LLM to another, oh and - the cost all of of this. So, so expensive.

New comment by VadimPR in "Claude Code Remote Control"

VadimPR — Wed, 25 Feb 2026 15:11:58 +0000

Pretty happy to see this. I've previously tried happy.engineer for this, but that wanted my Anthropic API token for itself (!) which is a no-no.

Seeing how the labs tend to copy the best functionality in any FOSS developments, I decided to wait - happy I did, here's the official functionality for this that is much more trustworthy.

New comment by VadimPR in "The Day the Telnet Died"

VadimPR — Wed, 11 Feb 2026 11:44:44 +0000

One reason would be to play MUDs, which are very well and alive these days!

New comment by VadimPR in "The Day the Telnet Died"

VadimPR — Wed, 11 Feb 2026 11:41:39 +0000

Lots of text games - MUDs - still play over telnet using dedicated MUD clients that implement their own telnet stack. Outright blocking the port has an outsized side efffe on them, this is simply not right.