HNHacker News
TopNewBestAskShowJobs

lmf4lol

521 karma · joined October 10, 2024

Building souvereign AI at https://www.bluehouse.app
submissionscomments
lmf4lol··on AI handles incidents, engineers lose touch with their systems
ah. when you wrote „hired as an expert“, I misread it as him being a contractor.

nevermind

lmf4lol··on Shopify is moving from React Native back to Swift and Kotlin
Yesterday, just before bedtime, I pointed Astra at our Electron Desktop app, and asked it to write me a native Swift app for iOS. The electron app has 750 unit tests and 50 something integration tests. It also had access to the electron app via mcp and could click around and inspect it. I also gave Astra read only access to the backend code.

It worked for 3 hours and delivered a nearly feature complete port. Today, I found in manual testing 3 bugs and 1 performance issue, all of which it fixed afterwards. To fix the performance issue , it made several different builds and profiled them with Xcode.

At around 12:30 I had a full native app port of our product on my iPhone and iPad and could show it to my crew. It even did portrait and landscape correctl!

Needless to say, that I was flabbergasted. On one hand, I love it , I can build now all those cool stuff, but on the other hand, its a complete devaluation of my craft. I kinda tell myself that I was still the one setting up a proper env for it and that not everyone can do it. but thats coping. Freaking coping… and I know it

lmf4lol··on AI handles incidents, engineers lose touch with their systems
Jesus Christ... and then?

What happened to him? What was the conclusion? Did he get paid?

lmf4lol··on GPT-6 Astra
listen to the DHH round two at Lex Friedman. Dropped a few days ago. Its inspiring
lmf4lol··on GPT-6 Astra
yes. There is plan mode in codex. I use it all the time. It will come up with a set of questions to clarify things
lmf4lol··on LLMs and Self-Referentiality
It was obviously meant as a funny joke ;-)

But on a more serious note. Humans "prompt" each other all the time. Especially in a Boss->Employee relation.

Defintion of "to prompt":

1. To cause or inspire: To make something happen or motivate someone to take action. For example, a loud noise can prompt you to look outside.

2. To assist or cue: To help an actor or speaker remember forgotten lines or words.

lmf4lol··on LLMs and Self-Referentiality
I concurrently prompt a senior human programmers and a set of AI programmers and the difference is the following:

The human applies critical thinking, questions choices, suggests his own ideas and has a certain taste. I also can prompt him, leave for 2 weeks, come back and have a result. And I can trust that it works! Velocity is OK. I often wish he would be faster :-)

The AI needs baby sitting and steering. It codes like a champ but I cant trust it. So we have 2000+ unit tests to make sure stuff worlks. The AI happily goes down into any rabbit whole I send it, so I need to constantly steer it. It has no taste st all, essentially everything is „A great idea“. However, its velocity is awesome. We build tons of featurs in no time. but lets not talk about the code, ok? :-)

I dont think Ill fire the human nor the agents. Both bring a lot of value

lmf4lol··on Was modern art a CIA psy-op? (2020)
until you begin to really LOOK at it
lmf4lol··on Antiqua–Fraktur dispute
I love Fraktur so much. When I look for books from Germans pre ww2, I always go for the ones in Fraktur. The aesthetic is so beautiful and pleasing. Just yesterday, I acquired two books , one from Schopenhauer and one from Kant in prints from 1860 and 1890 respectively. Still looking for a Faust in Fraktur, but they are really expensive … f*ck Hitler for banning Fraktur. it would be awesome if we Germans would still use it.
lmf4lol··on Nobel Disease
are ethics man-made or „given“ to us by god, the watchmaker or the universe?
lmf4lol··on Harness Engineering for Self-Improvement
The dream of the AI lisp machine ! Did you build in the functionality that the agent can on the fly rewrite its own (harness)-code?
lmf4lol··on Kimi-K3 on HuggingFace
Hey. Thats looks really cool. Thanks!
lmf4lol··on Kimi-K3 on HuggingFace
I love fireworks.ai! They launched it couple of hours ago and we have it now already live on our platform for our users. Just a shame they deprecated the on-demand flux models :( Where do I get my fix for image gen now?
lmf4lol··on Show HN: Physically accurate black hole you can put in your room
would be nice to have a “make foto” button for mobile
lmf4lol··on The relay market powering token resellers and fraud
thats one of the reasons why we vest any of our new customers. We need to know you before you are allowed to use our agent system. When you have an open sign up with some free credits, all hell breaks loose.
lmf4lol··on Show HN: Palmier Pro – Open-source macOS video editor built for AI
then please offer flexibility. I am looking for sth like that , but i want a prepaid based solution and not another sub.
lmf4lol··on Demis Hassabis has a plan to harness AI safely
regarding your headache diagnosis. If you just ask: could my headache be a brain tumor, the answer is probably: very unlikely but it might be. thats because its actually true. there is actually a non 0 chance that headache is a symptom of a brain tumor. From a bayesian standpoint though its really super super unlikely, especially if there are no other symptoms that might shift the prior.

a better way to use an LLM here is to let it research scientific papers (or medical guidelines) on headaches. then give it as much info on your symptoms as possible, and then ask it do deduct potential diagnoses. You can even ask it to calculate probabilities if thats what calms you down. Probabilities based on studies and available information. IMHO, this always leads to a more rational response.

maybe you are doing this already, idk. just wanted to share what works for me.

lmf4lol··on Show HN: OpenClawMachines – Extending OpenClaw to the Enterprise
what did you guys settle on? did you abandon the idea of personal agents completely or did you move to another harness and/or approach?
lmf4lol··on Underwater suit-wearing cyborg insect capable of diving and terra-aqua travel
i never ever had a fly bite me… what sort is that?
lmf4lol··on Underwater suit-wearing cyborg insect capable of diving and terra-aqua travel
What is , in your moral judgement, the difference between a fly and butterlies and wasps? why kill one but guide out the other?
lmf4lol··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
Its still business and eager entrepreneurs doing the work! Not China. China is facilitating, yes. but its not building models.
lmf4lol··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
Not the EU should build one but companies from the EU!!! We need to stop relying on the Brussel bureaucrats. China is not building models. US is not building models. Deepseek is doing and Anthropic!
lmf4lol··on DeepSeek V4 Peak Valley Pricing Change
It is truly sad to see what is happening to the UK.
lmf4lol··on Professor denounces mass AI fraud on an exam at Brown
> Now, I try to take notes during a meeting and my hand cramps. And as a bonus, my handwriting never was great, but now it's illegible for me.

Are you using a fountain pen, writing cursive and do you take care to hold it properly? Those three things fixed all my cramps

lmf4lol··on The origins of the school system aimed to produce independent, critical thinkers (2024)
we had a pretty good education system. But it got much more worse in the last decade(s).

And this is not only my personal anecdote, There are numerous studies on this. One for instance, that really shook me, reported that around 1/3 of graduates from the “practical level” of secondary school cant tell you what a newspaper article was about after reading it. And this was not the case “back in the days”.

Germany has the same problem btw. They perform less and less well at all kinds of standardized tests. Just like the Dutch.

So there is sth seriously wrong!

lmf4lol··on The origins of the school system aimed to produce independent, critical thinkers (2024)
I was just reading Schillers letters on the Aesthetic Education of Man. It made me sad that we have such profound insight available on beauty and a fulfilling life, and still produce a school system that is completely contrary to a proper human existence.

I also vividly recall pg’s reflections on the school system in Hackers and Founders. He was spot on with his observations and still is. My own experience made so much more sense. He wrote that a decade ago it hink. Still, Nothing changed!

I have two daughters. One just finished primary school and the second is halfway through primary. Its a disaster. They dont learn proper reading and math, they dony learn creativity. Its just a big waste of time sending them there to be honest. Heck, they watch 1 hour of stupid TV shows there everyday.. why??? My wife home schools them additionally, so that they learn proper reading, math, history & art. Its sad that this is necessary. My daughters excel now all tests obviously but its frightening to see how low the average skill level of their peers is. there are 12 year olds who cant read a paragraph or do simple maths in their head. They dont know anything about the history of the country.. Its terrifying that this is the future generation. They need to carry the torch after all.

And its not the kids fault. WE as a society failed them!!!!

ps i am from Amsterdam, NL btw

lmf4lol··on Previewing GPT‑5.6 Sol: a next-generation model
We are also using fireworks as our model provider. Our harness is openClaw, so tasks are not only coding but all kinds of tasks. For instance, I asked to fetch some info from the web via Chrome browser and to collect the info in an MD. The MD never appeared, even though it claimed to. I asked it three times to write the MD and it was always: “oh yes, I do it now..” then nothing. The search itself also was very bad because it just gave up after one page and hallucinated an answer and - even worse :-) - told me it was very thorough…

Pro aced the task :-)

But maybe its a config issue.

lmf4lol··on Previewing GPT‑5.6 Sol: a next-generation model
We rolled out Deepseek V4 Flash to our customers and it was an absolute disaster, unfortunately. It was not able to follow simple commands, always "forgot" to do things, lied consistently about its work, and so on. It was pretty good though on on-off work, like summarizing something or executing simple commands, so we are experimenting now with using it for subagent work with clear instructions and hand off.

Deepseek V4 Pro on the other hand is a really really good main driver and we have a lot of success using it. Its not Opus or GPT-5.5 level but on its way. Kimi 2.6 as well btw.. so there is already quite some choice.

lmf4lol··on Can you see three trees?
One thing that I really really like about living in Amsterdam, is that we have trees and plants everwhere. Also, for 2 years now, city stopped cutting most of the plant growth in parks and on the side of roads. Its so beautiful green and colourful now and insects are having a great time. I counted this year already 6 different sorts of humblebees in my garden.
lmf4lol··on .gitignore Isn't the only way to ignore files in Git
Wow! How did I not know this? I am a professional software dev for 20 years… and only ever used .gitignore !

I just realized that I never even „asked“ myself if there might exist a better way than to clutter .gitignore with all kinds of specific excluded only relevant to me. I just accepted the world as it appeared to me…

And Today, it got s little bit better :-)

← PreviousPage 2 of 5Next →