Hacker News: lodovic

New comment by lodovic in "Microsoft Edge is about to lock out older ad blockers, just like Chrome did"

lodovic — Sun, 09 Aug 2026 04:41:21 +0000

Try refreshing Firefox. On opening it shows two recommendations for Google; a large "VPN" button in the address bar; a toast asking me for my weather location; the address bar tries to cross sell me three Mozilla products: "Monitor, Relay and VPN".

I'm not sure how the new AI stuff works as I never enabled it, but apparently that's there, too.

New comment by lodovic in "Taste Is All That's Left"

lodovic — Fri, 07 Aug 2026 04:31:31 +0000

I think babysitting the AI would be a better term than vibe coding. At work they call it "AI assisted engineering" and "synthetic coworkers"

New comment by lodovic in "LG to ban residential proxies from smart TV apps"

lodovic — Wed, 22 Jul 2026 06:22:51 +0000

I have a separate lan for untrusted devices, I only use whitelisting. No public DNS for these devices.

New comment by lodovic in "LG to ban residential proxies from smart TV apps"

lodovic — Wed, 22 Jul 2026 06:14:58 +0000

I'm always wondering how hard it would be to just remove the hardware for spying. Just keep enough hardware to make it a dumb panel, remove the webos logic boards, wifi antenna, etc.

New comment by lodovic in "Geosql: A Claude/Codex skill for geospatial data"

lodovic — Wed, 08 Jul 2026 12:07:59 +0000

This can be very useful for urban planning. you could have an agent investigate the optimal spot for a new datacenter, examine solar power installations, and so on.

New comment by lodovic in "Every new car sold in the European Union must include a driver monitoring camera"

lodovic — Wed, 08 Jul 2026 07:46:03 +0000

I have the same sentiment. Who assures me this video isn't sent to the manufacturer for "quality control" reasons? Can it be used in court in case of an accident? Will my insurance ask access to monitor my driving? Can it be used for detecting phone use? Therefore, these cameras get a sticker, or a small printout of my head, looking alert, put in front of the camera. These systems only cause extra distraction, they do not reduce it - it feels like having a constant driving exam.

New comment by lodovic in "Leaking YouTube creators' private videos"

lodovic — Sun, 05 Jul 2026 11:28:58 +0000

That would put full blame on the tech staff and let the C-suite get away. The success of a software product is measured by sales and user base, so the more successful their sales and marketing are, the higher the damages will be for the tech staff.

I am of the opinion that companies and their management should be personally liable for damages caused by bad software, not their employees. They created the structure, hired everyone (and perhaps didn't hire QA), and invested in it to make a huge profit.

New comment by lodovic in "Ask HN: Why is the HN crowd so anti-AI?"

lodovic — Sat, 06 Jun 2026 05:42:58 +0000

I don't think they'll let the chain of managers above you handle the llm directly. That is just too much risk of incompetence. Instead, there will be micro teams (1 dev, 1 sre, 1 product owner) that are meta manageed by a LLM. And their llm reports directly to a higher up's llm. And software will diversify to prevent all these supply chain attacks we've seen lately.

New comment by lodovic in "Ask HN: What was your "oh shit" moment with GenAI?"

lodovic — Sat, 06 Jun 2026 05:30:01 +0000

The first time I pasted a screenshot of a PR review thread, adding just "I had some review comments, fix them" - and it perfectly solved everything, made small commits, and pushed it upstream - this was such a shock.

I now try to keep pushing the boundaries and see where it stops understanding my intention. Give it impossible tasks, gigantic projects, complex architectures. Last result: I wrote a complete OS including MPI, TCP/IP, and a GUI from scratch in only a week, while investing just a few hours a day in it. It even runs Doom!. Coding as a profession is over, but there's such a difference between the result if you approach this with a professional mindset, that I think the software engineering discipline can still provide massive value.

New comment by lodovic in "AI outperforms law professors in Stanford Law study"

lodovic — Wed, 03 Jun 2026 17:14:24 +0000

I now foresee a future where law firms have models trained on all the transcriptions of individual judges, lawyers and prosecutors, and run agents against them to decide on the optimal strategy for a case.

New comment by lodovic in "EU Age Control: The trojan horse for digital IDs"

lodovic — Sun, 26 Apr 2026 07:23:40 +0000

I doubt everyone will still be carrying phones as we know them in a decade, so we might indeed be headed for a future where governments keep giant databases of biometric information. Works OK if you trust your government to handle that properly and not abuse it in the future. The real headache is crossing borders, where your details end up in the hands of a foreign state.

New comment by lodovic in "Meta to start capturing employee mouse movements, keystrokes for AI training"

lodovic — Wed, 22 Apr 2026 10:39:22 +0000

That domain is for sale. This whole thread sounds like one of these "I sell ai agents as a saas and make 30k/month" stories.

New comment by lodovic in "Thoughts and feelings around Claude Design"

lodovic — Sat, 18 Apr 2026 22:02:14 +0000

"I have an error when i click on the orange button, see screenshot. fix it."

New comment by lodovic in "Claude Design"

lodovic — Sat, 18 Apr 2026 05:41:25 +0000

Exactly, these hotel chains guarantee a sort of minimum quality level which is sufficient for most people. No surprises.

New comment by lodovic in "President Trump bans Anthropic from use in government systems"

lodovic — Sat, 28 Feb 2026 08:43:07 +0000

Grok is quite good for explaining tweets, summarizing meme videos and chatting about celebrities. But chat and image inference only, it was performing really poor in agentic work the last time I tried.

New comment by lodovic in "President Trump bans Anthropic from use in government systems"

lodovic — Sat, 28 Feb 2026 05:41:10 +0000

Addidionally: Why wasnt X.ai considered before Openai? also noted a lot of hate from Musk towards Anthropic lately.

New comment by lodovic in "Show HN: LocalGPT – A local-first AI assistant in Rust with persistent memory"

lodovic — Sun, 08 Feb 2026 07:12:39 +0000

I made something similar to this project, and tested it against a few 3B and 8B models (Qwen and Ministral, both the instruction and the reasoning variants). I was pleasantly surprised by how fast and accurate these small models have become. I can ask it things like "check out this repo and build it", and with a Ralph strategy eventually it will succeed, despite the small context size.

New comment by lodovic in "How Google got its groove back and edged ahead of OpenAI"

lodovic — Thu, 08 Jan 2026 07:43:31 +0000

I tried to sign up for Gemini this weekend but gave up after an hour. I got stuck comparing their offerings, looking for product pages, proper signup, etc. Their product offering and naming is just a mess. Cloud console. AI studio, I was completely lost at some point.

New comment by lodovic in "Show HN: Z80-μLM, a 'Conversational AI' That Fits in 40KB"

lodovic — Mon, 29 Dec 2025 07:46:50 +0000

I love these thought experiments. Looking at the code size, it would have been possible for someone to come up with this back in the days, similar to the idea of a million monkeys on a typewriter eventually producing Shakespeare.

New comment by lodovic in "A guide to local coding models"

lodovic — Wed, 24 Dec 2025 06:15:57 +0000

I always start in the Claude CLI. Once I hit the token limit, I can do two things: either use Copilot Claude to finish the job, or pick up something completely different, and let the other task wait until the token limit resets. Most importantly, I'm never blocked waiting for the cap.