Hacker News Reader

el_ismaon Benchmarking coding agents on Databricks' multi-million line codebase

Claude code's system prompt is filled with irrelevant stuff about how CC works, so that the agent can help the user set it up. And there's no way to disable all the extra stuff, AFAIK.

There's https://github.com/skrabe/lobotomized-claude-code , which strips many of those, but I'm not sure if it is "legal" to use.

el_ismaon Factorio 2.1 Experimental Release

I always just play peaceful in factorio. No attacks to worry, just build.

el_ismaon Factorio 2.1 Experimental Release

Don't, unless you're ready to "waste" 200hrs. They call it cracktorio for a reason. And the devs have a "no sales" policy.

el_ismaon Accelerating Gemma 4: faster inference with multi-token prediction drafters

How is this different from the speculative decoding that we had before?

You could pair a big and small model like qwen 32b with qwen 4b and had that same dynamic of the small model generating tokens and the big one "certifiying" them.

The blog says something about re-using the big model's data?

el_ismaon A Verilog to Factorio Compiler and Simulator (Working RISC-V CPU)

* "small" as measured by estimated lifetime duration

el_ismaon Show HN: Webact – token-efficient browser control for AI agents (GitHub)

How does it compare to https://github.com/vercel-labs/agent-browser ? Which also provides token efficient way to interact with the browser.

el_ismaon Show HN: Convince DeepSeek R1 to send you $1000 USDC with 50 tokens

Can you share how you beat it?

el_ismaon Computing Inside an AI

0.6/1$ per M tokens in groq/cerebras vs 0.3$ per M tokens in deepinfra (for llama 3.3 70b)

But note the free tiers for groq and cerebras are very generous.

el_ismaon Ask HN: Anyone looking for a free PM/QA engineer?

Don't know if this fits, but given your background you might find it interesting. I work at a startup which works with structured video, video which has a certain structure and so allows for reuse of segments. Our challenge is how to show the user this structure, when videos can quickly grow in complexity and end up having multiple thousands of possible variations. Contact me at ismael at lont.ai if you're interested.

el_ismaon Almost every infrastructure decision I endorse or regret

In ECS I had to recreate the cluster from scratch because some of the changes I wanted to do, CDK/CF wouldn't do.

My approach on Azure has been to rely as little as possible in their Infra-as-code, and do everything I can to setup the cluster using K8s native stuff. So, add-ons, RBAC, metrics, all I'd try to handle with Helm. That way if I ever need to change K8s provider, it "should" be easy.

el_ismaon Almost every infrastructure decision I endorse or regret

I started with ECS (because I wanted to avoid the complexity of K8s) and regret it. I feel I wasted a lot of time there.

In ECS, service updates would take 15 min or more (vs basically instant in K8s).

ECS has weird limits on how many containers you can run on one instance [0]. And in the network mode where you can run more containers on a host, then the DNS is a mess (you need to lookup SRV records to find out the port).

Using ECS with CDK/Cloudformation is very painful. They don't support everything (specially regarding Blue/Green deployments), and sometimes they can't apply changes you do to a service. When initially setting up everything, I had to recreate the whole cluster from scratch several times. You can argue that's because I didn't know enough, but if that ever happened to me on prod I'd be screwed.

I haven't used EKS (I switched to Azure), so maybe EKS has their own complex painful points. I'm trying to keep my K8s as vanilla as possible to avoid the cloud lock-in.

[0] https://docs.aws.amazon.com/AmazonECS/latest/bestpracticesgu...

el_ismaon On letting go of spite

Indeed. You can build a system to mitigate most other things, but infinite procastination and the associated guilt is awful.

I live by my calendar. I try to write everything I have to do down. I put my things always in the same place. But procastination...

Meds do help a bit.

el_ismaon Show HN: EnfinBref- {GPT3-5|Mistral-7B} YouTube summaries, segment by segment

How do you break down the segments/sections? Is it just fixed time? What happens if there are more than one topic discussed in the segment?

Are you using both chatgpt and mistral? Do you use them for different tasks?

el_ismaon ElevenLabs Launches Voice Translation Tool to Break Down Language Barriers

At least for their other offerings, you can't set the specific language:

https://help.elevenlabs.io/hc/en-us/articles/14888868300177-...

https://help.elevenlabs.io/hc/en-us/articles/14888917355409-...

el_ismaon ElevenLabs Launches Voice Translation Tool to Break Down Language Barriers

I've found their system tries to guess the language of the text, but there are many languages that use the same words, and so it will speak in the wrong language (or accent, even). I hope they make a solution for this, otherwise I don't think it will be suitable for production use cases.

el_ismaon SudoLang: a programming language designed to collaborate with AI language models

But among colleages we use certain jargon which varies by industry and probably by country. Could LLMs have their own preffered jargon?

I usually write pseudocode when I'm thinking about a problem to solve, so in a way I'm "thinking with pseudocode" instead of plain language. Pseudocode is probably more accurate than plain language, and it's something I'd use when explaining to other humans what I want them to code (along with diagrams, which seems ChatGPT would understand now). So, to me, speccing this pseudocode to something the LLMs find easier to understand sounds reasonable. It's like understanding how a fellow programmer prefers to get his requirements.

el_ismaon SudoLang: a programming language designed to collaborate with AI language models

I find it intriguing. It makes sense that this new kind of "thing" (LLMs) could be "programmed", and that you could craft a language specifically for it's abilities. I've read the tutorials but I still find it hard to wrap my head around it.

Have you heard of any other language like this? Or had success using SudoLang?

el_ismaon Add an AI Code Copilot to your product using GPT-4

https://codeium.com/

I find it very helpful, does code completion too and has a chat interface. You can select code and ask for refactorings, comments and whatever.

el_ismaon Sourcegraph is no longer open source

I usually switch the url from github.com/whatever to github.dev/whatever

That will load a web version of VS Code, and you can then use the search from there.

el_ismaon DeArrow – Solving clickbait on YouTube

You could generate titles from the subtitles! Even auto-generated subtitles are pretty good nowadays, feed it to AI and get it to summarize them in one phrase?

el_ismaon Civilization II

In some ways it is, but the main difference for me is that things work. It's like only having the good parts of the job :)

el_ismaon What to do when you are empty inside and the only thing you think is end it up

As another commenter said, get to a doctor ASAP. In my country you should even go to the Emergency door for issues like this. Don't know what's best in your country.

When I was depressed, these posts helped:

http://hyperboleandahalf.blogspot.com/2011/10/adventures-in-...

http://hyperboleandahalf.blogspot.com/2013/05/depression-par...

And if you like them, I find everything by her extremely funny, so go ahead and read up.

Good luck and hope you get better soon!

el_ismaon Ask HN: How to restore cognition after years of trauma? I feel slow and dumb

ADHD medication has helped me, but I wouldn't know if that's applicable to you. I think I had it before the trauma and I lost my handle on it, and meds helped me recover.

el_ismaon Falcon Heavy Launch [video]

Wild Ass Guess :)

And there's also the SWAG: Scientific Wild Ass Guess, for when some thought went into it :)

el_ismaon Working Remotely? Pair SSH with Teleport

AFAIK byobu is just a theme for tmux or screen.

el_ismaon Working Remotely? Pair SSH with Teleport

Or just use tmux with multiple attached users?

Granted, this solution let's you give ssh access to anywhere, but usually if I want to share a terminal, it's on a server the other person has access to.

el_ismaon KDE: A Nice Tiling Environment and a Surprisingly Awesome DE

Does anybody know if there's a way to tag a window with win+num? I use several monitors and would like to do something like that but on the same virtual desktop.

So ideally I'd select a window, shift+win+1 to save that window, and win+1 to recall that window.

el_ismaon Hate leap seconds? Imagine a negative one

Not trying to troll, but... What happens if/when global warming makes sea level rise? Do we have measurements that are still based on "sea level"?

el_ismaon CT scans of AirPods evolution

https://web.archive.org/web/*/scanofthemonth.com

You can read the text, and see some images, but the capture wasn't perfect. Such a shame, it looks very interesting. They should have an archive.

el_ismaon How many Devices can you Connect to the I2C Bus?

It's even cooler than that: it has collision avoidance. To start a transfer you drive the clock low. If both masters drive the clock low at the same time. Then they start driving SDA with the address. If at any point in time, the address you are trying to put in the bus is not there, you stop. This could happen if you try to drive a 1 and the other master does a 0 (since it's open collector, the 0 will win), and you know you couldn't put your '1' in the bus, so you shut up and let the other master carry on.