HNHacker News
TopNewBestAskShowJobs

baalimago

1,295 karma · joined July 16, 2017

learning...

https://github.com/baalimago https://lorentz.app

submissionscomments
baalimago··on Goodbye Visa and Mastercard: 130M Europeans switching to sovereign payment
Good! Now please remove dependency of alphabet + apple for bank apps, and we're golden.
baalimago··on Gemini 3.5 Flash
What happened to gemini 3.2, 3.3, and 3.4..?
baalimago··on Grok Build
Do we really need another one of these..?
baalimago··on Googlebook
Oh boy will this be dated in 2 years
baalimago··on Just Use Go
Lack of extensive standard library, for one. But yeah Java is pretty great. Spring boot/quarkus especially
baalimago··on Just Use Go
I read this, as my computer crashed while compiling a 1000 dependency CRUD rust app, for the fourth time today. Then I take a deep breath.
baalimago··on Google Cloud fraud defense, the next evolution of reCAPTCHA
Captcha suggestion: force users to write something offensive/vulgar (we have a few "banned words"). Or to take a stance in Israel/Palestine.

Whatever the response is, it'll unlikely be from an LLM.

baalimago··on Agents can now create Cloudflare accounts, buy domains, and deploy
Genius! Automate the flow for making customers spend money.
baalimago··on Train Your Own LLM from Scratch
Yeah it's just a semantic pet peeve. Let me ask you this: What is a "Language Model", if this is a "Large Language Model"? Inversely, if a 1.5B model is "Large" then what is the recent 1T param models? "Superlarge"?

In my own very humble opinion, it becomes "Large" when it's out of non-specialized hardware. So currently, a model which requires more than 32GB vram is large (as that's roughly where the high-end gaming GPUs cut off).

And btw, there is no way you can train a language model on a CPU, even with ddr5, lest you wait a whole week for a single training cycle. Give it a go! I know I did, it's a magnitude away from being feasible.

baalimago··on Train Your Own LLM from Scratch
Train your LM from scratch*

I doubt you have a machine big enough to make it "Large".

baalimago··on Alert-driven monitoring
My solution to this is to have leveled alerts. Some are... recommendations, the ones which you look at with a glance to get a heads up about something being wrong. These are the ones which OP would claim cause alert fatigue, most likely.

Then I have a second level of this, the superpanic. Here is the "true" alert, which means "drop all things, fix this now". On every superpanic, there are stricter routines which intentionally cause friction, such as creating tickets about said superpanic, potentially hosting post mortems etc. This additional manual labour encourages tweaking the levels of the superpanic so that they sometimes are more lack, sometimes stricter, depending on the quality of the deployed services + the current load.

What signals a superpanic? Key valuable functionality being offline. Off-site uptime-checkers assuring that all primary domains resolve + serve traffic, mostly. Also crontime integration tests of core functionality. Stuff like that.

baalimago··on Ti-84 Evo
Conclusion from reading HN comments: very few used the calculator to actually calculate anything
baalimago··on GPT-5.5
Well, sort of. Imagine the case where it first scans the repo, then "intelligently" creates architecture files describing the project. The level of intelligence will create a varying quality of summary, with varying need of deep-scans on subsequent sessions. Level of intelligence will also increase comprehension of these architecture files.

Same principle applies when designing plans for complex tasks, etc. Token amount to grasp a concept is what matters.

baalimago··on GPT-5.5
Worth the 100% price increase over GPT-5.4?
baalimago··on ChatGPT Images 2.0
"Benchmarks" aside, do anyone actually use these image models for anything?
baalimago··on NASA Artemis Posters
Ah, my bad. I thought that was the source, but seems like the DB I found the high quality versions was elsewhere. Search for the "PIA number" of the images to find the high-res versions, example:

https://www.nasa.gov/image-detail/amf-as11-40-5915/

https://www.google.com/search?q=as11-40-5915

https://www.lpi.usra.edu/resources/apollo/frame/?AS11-40-591...

baalimago··on NASA Artemis Posters
If you're into this, check out the Apollo 11 gallery[1]. Contains very high-quality images from the actual trip, including "not so common" pictures from the moon.

[1]: https://www.nasa.gov/gallery/apollo-11/

baalimago··on GitHub Stacked PRs
Sounds like a merge-conflict nightmare
baalimago··on ARC-AGI-3
You can tell it's an AI by it not becoming utterly by playing the "game". I could personally not stand any more than the first level.
baalimago··on Why I love NixOS
If I say "Girlfriend, I love equally to my operative system" I'm in for a world of trouble.
baalimago··on Why I love NixOS
To me, loving inanimate "trivial" things diminishes the value of love. I love my girlfriend and my pets. I like my kitchen knife and my car. To bunch up both into the same category confuses things into "which one do I love the most", some sort of spectrum of love.

In the case of a fire, I'm sure you wouldn't prioritize your laptop with NixOS over your cat (let's imagine that the only backup is in the house that's on fire).

baalimago··on Why I love NixOS
"Loving" any OS is strange to me. It's just a tool. I don't love my kitchen knife, or car. Nor do I love my computer, or any application on it.

Web3, Rust, NixOS. The holy trinity of cult-like appreciation. I do wonder what brings forth such fanaticism.

baalimago··on How we give every user SQL access to a shared ClickHouse cluster
The evolution of this is to use agents, and have users "chat with the data"
baalimago··on Edge.js: Run Node apps inside a WebAssembly sandbox
The idea, as I understand it, is not to run edgejs multitenant in the sense that have multiple tenants under the same edgejs process. Instead, you spawn one edgejs process for each tenant. So in the openclaw example each sandboxed call would be a new edgejs process.
baalimago··on SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI
It's there, you just need to use it with the responses API. Set model field to 'gpt-5.3-codex'
baalimago··on SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI
Replace "Agent" with "Employee" and apply the same algorithm. Evaluate employee efficiency. Profit?
baalimago··on An autopsy of AI-generated 3D slop
I do wonder what the outcome would've been had the 4 hours been spent in perfecting the input to the AI-generator. It's not a fair comparison if the same amount of time is not spent on both.

How good mesh can a human produce in the time that it took for the gen-AI?

baalimago··on How I use Claude Code: Separation of planning and execution
Another approach is to spec functionality using comments and interfaces, then tell the LLM to first implement tests and finally make the tests pass. This way you also get regression safety and can inspect that it works as it should via the tests.
baalimago··on The path to ubiquitous AI (17k tokens/sec)
I've never gotten incorrect answers faster than this, wow!

Jokes aside, it's very promising. For sure a lucrative market down the line, but definitely not for a model of size 8B. I think lower level intellect param amount is around 80B (but what do I know). Best of luck!

baalimago··on I tried building my startup entirely on European infrastructure
There is an ongoing lobbying push for "Made in EU" [0] which is unrelated to OPs article. The winds sure are blowing towards European sovereignty. Thanks, Trump!

[0]: https://www.euronews.com/business/2026/02/19/made-in-europe-...

← PreviousPage 4 of 13Next →