Hacker News: tigranbs

Voice Layer for AI Agents Built with Rust, Pluggable to All Agentic Frameworks

tigranbs — Fri, 23 Jan 2026 09:37:31 +0000

Article URL: https://github.com/SaynaAI/sayna

Comments URL: https://news.ycombinator.com/item?id=46730433

Points: 1

# Comments: 0

New comment by tigranbs in "The Vibe Coding Hangover: What Happens When AI Writes 95% of Your Code?"

tigranbs — Wed, 31 Dec 2025 18:28:50 +0000

Current AI coding assistants are not just a Stack Overflow replacement; they do a pretty good job writing whole projects without you touching the code. At the end, when the coding guidelines are not clearly defined, the AI-generated codebase becomes messy and unmaintainable. That is why, nowadays, it has become profitable for my team to fix the "vibe-coded" products that are working fine but have a shit ton of problems with scaling and implementation logic.

The Vibe Coding Hangover: What Happens When AI Writes 95% of Your Code?

tigranbs — Wed, 31 Dec 2025 16:40:39 +0000

Article URL: https://sayna.ai/blog/the-vibe-coding-hangover-what-happens-when-ai-writes-95-percent-of-your-code

Comments URL: https://news.ycombinator.com/item?id=46445701

Points: 2

# Comments: 2

New comment by tigranbs in "Securing AI coding agents: What IDEsaster vulnerabilities should you know"

tigranbs — Tue, 30 Dec 2025 20:33:26 +0000

Security researchers have revealed 30+ CVEs affecting Claude Code, Cursor, GitHub Copilot and others via prompt injection and MCP tool poisoning; this article covers attack vectors, the OWASP agentic AI Top 10 and practical defences.

Securing AI coding agents: What IDEsaster vulnerabilities should you know

tigranbs — Tue, 30 Dec 2025 20:33:26 +0000

Article URL: https://tigran.tech/securing-ai-coding-agents-idesaster-vulnerabilities

Comments URL: https://news.ycombinator.com/item?id=46437660

Points: 1

# Comments: 2

Coding Rust with Claude Code and Codex

tigranbs — Mon, 22 Dec 2025 20:24:12 +0000

Article URL: https://tigran.tech/coding-rust-with-claude-code-and-codex/

Comments URL: https://news.ycombinator.com/item?id=46358577

Points: 2

# Comments: 0

New comment by tigranbs in "You can now play Grand Theft Auto Vice City in the browser"

tigranbs — Fri, 19 Dec 2025 20:11:17 +0000

Links times out, seems the host wasn't ready for the HN traffic!

New comment by tigranbs in "Cloudflare Radar 2025 Year in Review"

tigranbs — Thu, 18 Dec 2025 00:04:12 +0000

Wow, the internet has grown 19%, which is surprising that it is still growing at that rate over the year.

New comment by tigranbs in "Why do commercial spaces sit vacant?"

tigranbs — Wed, 17 Dec 2025 21:33:08 +0000

Living in SoCal, I almost always prefer to order online. Most local businesses are losing to their e-commerce competitors; no wonder commercial spaces are empty.

I have a side business of a small e-commerce shop. I would consider having physical space just for the sake of luxury, but now I would rather spend that monthly rent on marketing online rather than paying for physical space.

IMHO, that's what is happening. Bank problems or anything else are secondary; if it were profitable to be at the physical location for the businesses, other factors would vanish.

New comment by tigranbs in "How SQLite is tested"

tigranbs — Wed, 17 Dec 2025 19:04:22 +0000

Based on the stability track record, I was more curious about how SQLite has done the anomaly testing. Sadly, the article has just a few words about it.

Truly one of the best software products! It is used on every single device, and it is just pure rock-solid.

New comment by tigranbs in "AI's real superpower: consuming, not creating"

tigranbs — Wed, 17 Dec 2025 11:20:22 +0000

I would say the AI consumption aspect was a side effect: the primary goal was to "generate" new stuff. So far, to me, the significant boost is the coding aspect. Still, for the rest of the people, I think you are right: 90% of the benefits come from being an interactive, conversational search on top of the available information that AI can read/consume.

New comment by tigranbs in "Is Mozilla trying hard to kill itself?"

tigranbs — Wed, 17 Dec 2025 10:31:56 +0000

Firefox has been lagging in Web features for a long time. I have been a Zen browser user for about a year, and recently moved back to Arc just because almost all interactive websites look bad on the Firefox engine; somehow, they don't have the same level of JS API support as Chrome does, especially for WebRTC, Audio, or Video. And this is frustrating that they think the problem is the AdBlockers!

New comment by tigranbs in "Tesla reports another Robotaxi crash"

tigranbs — Wed, 17 Dec 2025 04:12:51 +0000

IMHO, this is not too bad! But obviously, coming from the software product industry, everyone knows that building features isn't the same as operating in practice and optimizing based on the use case, which takes a ton of time.

Waymo has a huge head start, and it is evident that the "fully autonomous" robotaxi date is far behind what Elon is saying publicly. They will do it, but it is not as close as the hype suggests.

New comment by tigranbs in "Show HN: Titan – JavaScript-first framework that compiles into a Rust server"

tigranbs — Wed, 17 Dec 2025 04:06:50 +0000

TBH, the idea seems way outdated for the current state of software engineering. The Rust compiler provides a massive benefit for AI Coding because it literally catches all the failure cases, so all AI have to do is implement the logical parts, which is usually a no-brainer for something like a Claude Code or Codex.

For example, the https://github.com/SaynaAI/sayna has been mostly Claude Code + me reviewing the stuff + some small manual touches if needed, but for the most part, I have found that Claude Code writes way more stable Rust code than JS.

It would be easier and safer to give the JS code to a translator and have it translate it into Rust, and then continue AI Dev with Rust, than to invest time in an automated compiler from JS to Rust. IMHO!

New comment by tigranbs in "Letta Code"

tigranbs — Tue, 16 Dec 2025 22:46:31 +0000

In my experience, "memory" is really not that helpful in most cases. For all of my projects, I keep the documentation files and feature specs up to date, so that LLMs are always aware of where to find what and which coding style guides the project is based on.

Maintaining the memory is a considerable burden, and make sure that simple "fix this linting" doesn't end up in the memory, as we always fix that type of issue in that particular way. That's also the major problem I have with ChatGPT's memory: it starts to respond from the perspective of "this is correct for this person".

I am curious who sees the benefits of the memory in coding? Is it like "learns how to code better" or it learns "how the project is structured". Either way, to me, this sounds like an easy project setup thing.

New comment by tigranbs in "The World Happiness Report is beset with methodological problems"

tigranbs — Tue, 16 Dec 2025 19:23:19 +0000

As a US person, I have lived in Finland for 3 years, and I can assure you that the Finns are the most content people you can imagine! They can go months without talking to anyone and still consider themselves "happy", but the correct word in English is "content".

That report is correct, it just they advertise with the wrong word in the headline, I guess because it is more click-bate title than having it as "The most content country"

New comment by tigranbs in "Show HN: A real-time 4D fractal explorer in the browser using WebGPU"

tigranbs — Tue, 16 Dec 2025 19:15:05 +0000

Nice! I am surprised that the JS compressed chunks are not that big. I have checked, and the largest is ~340Kb, which is even smaller than a regular Next.js starter kit home page.

Traditionally, we have a ton of components for 2D UI, but the UX still sucks for the most part. I am not even sure what it will look like to create the 3D UX for anything other than the Games. For example, nobody uses Unity for desktop or mobile apps, because the freedom of a 3D environment isn't suited to regular UI tasks.

New comment by tigranbs in "O'saasy License Agreement"

tigranbs — Tue, 16 Dec 2025 08:29:06 +0000

I used the MIT license for https://github.com/SaynaAI/sayna mainly because the challenge is usually in product velocity and direct sales/distribution. Blocking from SaaS is explicitly entirely redundant.

Making software is getting cheaper, so this kind of license would not protect against someone reverse-engineering the SaaS tool in a week. It is better to be abstracted away from those type of things IMHO

New comment by tigranbs in "Liquid-rust: Liquid templating for Rust"

tigranbs — Mon, 15 Dec 2025 22:07:04 +0000

Ah nice! I should integrate this into https://github.com/SaynaAI/sayna

``` Performant. Do the best we can within what is conformant. ```

Would be great to have benchmarks like ops/second

New comment by tigranbs in "Ford kills the All-Electric F-150"

tigranbs — Mon, 15 Dec 2025 22:03:12 +0000

Maybe it is just me, but the “universal” platform architecture seems a bit inefficient. I think, with a software-first mindset and modularity in Hardware products, it is insane to think efficiency first, especially when the goal is to make it cheaper to produce and operate.