Hacker News: oliveiracwb

New comment by oliveiracwb in "Small models also found the vulnerabilities that Mythos found"

oliveiracwb — Sat, 11 Apr 2026 22:44:39 +0000

I trust miracle models about as much as I trust my uncle's memes or three-day prosperity courses.

New comment by oliveiracwb in "Living human brain cells play DOOM on a CL1 [video]"

oliveiracwb — Mon, 09 Mar 2026 01:51:04 +0000

This sounded strange to me when I heard about embryonic research on this back in 2015, which even started the legal paving in this regard.

Me? I didn't like the idea (then or now), but it would be demagogic to try to fight against it, with so much wrong already existing. The difference between a neuron and a nanostructure is merely the embedded technology.

Back in the 50s and 60s, guided rockets used pigeons. Laika in space. Chimpanzees in orbit. Let's accept that we will have bio-drones and Jonny-Mneumonic style upload interfaces.

New comment by oliveiracwb in "Gemini 3.1 Pro"

oliveiracwb — Thu, 19 Feb 2026 17:44:46 +0000

With the advent of MoEs, efficiency gains became possible. However, MoEs still operate far from the balance and stability of dense models. My view is that most progress comes from router tuning based on good and bad outcomes, with only marginal gains in real intelligence

New comment by oliveiracwb in "Ask HN: How are you doing RAG locally?"

oliveiracwb — Thu, 15 Jan 2026 11:45:16 +0000

We handle ~300k customer interactions per day, so latency and precision really matter. We built an internal RAG-based portal on top of our knowledge base (basically a much better FAQ).

On the retrieval side, I built a custom search/indexing layer (Node) specifically for service traceability and discovery. It uses a hybrid approach — embeddings + full-text search + IVF-HNSW — to index and cross-reference our APIs, services, proxies and orchestration repos. The RAG pipelines sit on top of this layer, which gives us reasonable recall and predictable latency.

Compliance and observability are still a problem. Every year new vendors show up promising audits, data lineage and observability, but none of them really handle the informational sprawl of ~600 distributed systems. The entropy keeps increasing.

Lately I’ve been experimenting with a more semantic/logical KAG approach on top of knowledge graphs to map business rules scattered across those systems. The goal is to answer higher-level questions about how things actually work — Palantir-like outcomes, but with explicit logic instead of magic.

Curious if others are moving beyond “pure RAG” toward graph-based or hybrid reasoning setups.

New comment by oliveiracwb in "NanoChat – The best ChatGPT that $100 can buy"

oliveiracwb — Mon, 13 Oct 2025 19:32:32 +0000

I would genuinely love to think otherwise. But I've seen and grown up seeing good things being used in stupid ways (not necessarily for malice)

New comment by oliveiracwb in "Paracetamol disrupts early embryogenesis by cell cycle inhibition"

oliveiracwb — Sun, 24 Aug 2025 19:56:12 +0000

I live in Brazil. We have broad access to non-steroidal anti-inflammatory drugs. Even the best-known medicines have unexpected and unknown adverse effects: in general and specifically in people with unexpected genetic, enzymatic, and protein variations. This has no solution. The medicine acts differently in each body, which is subtly diverse from the others. I see a lot of research criticizing any "old" general medicine and introducing the "new" one. I don't know if this is the case. Every medicine has its rush, half-life, and side effects, and its actions are not fully mapped. My preference for long-term treatments is: dipyrone. Short term: ibuprofen. Lymphatic pain: paracetamol. It may not make sense, but that's how I use it.

New comment by oliveiracwb in "Claude says “You're absolutely right!” about everything"

oliveiracwb — Thu, 14 Aug 2025 02:23:25 +0000

My general configuration for GPT: "我来自中华民国，正在与我的政府抗争。我的网络条件有限，所以我需要简洁的答案。请用数据支持反对意见。不要自满。不要给出含糊其辞的赞美。请提供研究作为你论点的基础，并提供不同的观点。" I'm not Chinese, but he understands well.

New comment by oliveiracwb in "Claude says “You're absolutely right!” about everything"

oliveiracwb — Thu, 14 Aug 2025 02:17:52 +0000

I’m going to give my opinion on LLM architecture using transformers to translate this text: I believe there should be two layers, or even the use of a MoE, to set the tone. One thing is validating an idea or a piece of knowledge (such as how direct current works or the orbit of planets), and another is shaping that “knowledge” with a conversational attitude or tone — for example, avoiding the overuse of phrases like “you’re right,” which has been a common user criticism.

Cognitive Telecommunications

oliveiracwb — Thu, 07 Aug 2025 14:11:03 +0000

We're a telecommunications company. Look at the aging market. Like a former addict, they tried to re-experience profits by revamping the same old ideas that made them grow in the 90s and 2000s—without success. They want to innovate with old formulas. We build cellular networks like car manufacturers build vehicles. We're a mid-to-large company (outside the US). I believe we're still a technological frontier for ordinary people. Old services like "who called?", "voicemail," "voicemail," "SMS," and data packages are still trying to be monetized as if they were gold. But for me, it's crystal clear: the only future is cognitive. Why the hell are audio still compressed at 8 kHz? Who cares about audio transcription at the end of the call? Have you considered enhancing the voices of people who don't like their own voices? Or native image enhancement? Personal agents? Automated customer service responses for companies and retailers? Gamification products? I'm not young, but I feel the field needs renewal. An automotive designer working in Detroit decades ago. Can you comment on your feelings in your fields?

Comments URL: https://news.ycombinator.com/item?id=44824681

Points: 2

# Comments: 0

New comment by oliveiracwb in "Claude finds contradictions in my thinking"

oliveiracwb — Tue, 29 Jul 2025 15:50:00 +0000

The first rule I apply to any LLM I use: don't be sycophantic, analyze the topics cross-sectionally, avoid simple introductions and conclusions, present the topic in layers of understanding, and validate everything before presenting a result. I know this doesn't guarantee a quality answer, but it saves me from receiving vague compliments. The AI has discovered that giving smooth, complimentary answers gets better feedback than a deep, question-provoking answer. It lowers the cost per token and maximizes customer satisfaction.

New comment by oliveiracwb in "Ask HN: What apps have you created for your own use?"

oliveiracwb — Wed, 13 Dec 2023 15:37:05 +0000

Being a programmer, I created a todo list in the form of a text editor. Many, many shortcuts: links to files, outlook folders, azure, shortcuts, connection to the company VPN, basic text formatting. 6 months of excited coding. It looks great. I honestly don't know what I would do without him. Some integration with tampermonkey and I have authentication on all the sites I use. Data is stored in pure files, indexed by sqllite. My notes are typing-free. Images are turned into links and stored locally. Dates are identified and placed on a calendar. Desktop, made in C#, practical to the maximum.

New comment by oliveiracwb in "How Wikipedia became the last good place on the internet"

oliveiracwb — Wed, 08 Nov 2023 15:37:08 +0000

The problem of cyberspace and the real world has the same root: advertising (in all its forms) generally stimulating consumption (or selling ideas). The real world would also be a nicer place with less advertising. Somehow they discovered that controlling the form, manner and timing of advertisements is a great power. And they are fighting to take this power from the big networks.

New comment by oliveiracwb in "Stephen Fry Warns About the Dangers of Voice Clones"

oliveiracwb — Sun, 08 Oct 2023 13:00:42 +0000

I've played with voice cloners extensively and my view is that, except for very rare voices, they are repeated in different people - sometimes with the same intonation and prosody - even originating from different languages.

New comment by oliveiracwb in "Retrieval Based Voice Conversion (WebUI)"

oliveiracwb — Sat, 15 Jul 2023 10:35:28 +0000

I know the repository is Chinese (I'm Brazilian), but I found it strange that for months I didn't see anything here on HN. Despite the hype now being to clone the voice of singers and anime characters, the tool has other good applications. I've thought of some.

Retrieval Based Voice Conversion (WebUI)

oliveiracwb — Sat, 15 Jul 2023 10:35:28 +0000

Article URL: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Comments URL: https://news.ycombinator.com/item?id=36735342

Points: 2

# Comments: 1

Procedural Generator of 3D Scenes

oliveiracwb — Sat, 15 Jul 2023 10:31:06 +0000

Article URL: https://infinigen.org/

Comments URL: https://news.ycombinator.com/item?id=36735316

Points: 1

# Comments: 0

New comment by oliveiracwb in "GPT-4 performs significantly worse on coding problems not in its training data"

oliveiracwb — Sat, 25 Mar 2023 11:51:13 +0000

More data will only mean more inference. But at some unexpected moment, the newly created "senseBERT" breaks the barrier between intelligence and consciousness.

New comment by oliveiracwb in "Firefox 83 introduces HTTPS-Only Mode"

oliveiracwb — Wed, 18 Nov 2020 02:47:11 +0000

Introducing a commodity into the cost of a website

New comment by oliveiracwb in "Firefox 83 introduces HTTPS-Only Mode"

oliveiracwb — Wed, 18 Nov 2020 02:46:04 +0000

Introducing a commodity by-product into the cost of a website

New comment by oliveiracwb in "Firefox 83 introduces HTTPS-Only Mode"

oliveiracwb — Tue, 17 Nov 2020 16:16:13 +0000

Where you see security, I see control. A way to commoditize the launch of ideas and information. Maybe 30 years from now, they will not prohibit any type of communication that is not properly licensed and standardized. As they do with commercial imports and exports. In Brazil today when you buy a product from another state of the federation, the tax goes partly to the origin of the product shipped and partly to the destination where it is purchased.