HNHacker News
TopNewBestAskShowJobs

alienbaby

406 karma · joined March 9, 2016

submissionscomments
alienbaby··on Stop Forwarding Errors, Start Designing Them
What is it you are actually warning me of?
alienbaby··on Ask HN: When do we expose "Humans as Tools" so LLM agents can call us on demand?
now the computer decides what it needs, and we bid our time lower and lower to accomplish the task .. :/

Maybe I write a bot that answers fivverr requests at the lowest price possible. We can all race to the bottom.

alienbaby··on Nerd: A language for LLMs, not humans
This describes where we are at now. I don't think it's the entire point. I think the point is to get it writing code at a level and quantity it just becomes better and more efficient to let it do its thing and handle problems discovered at runtime.
alienbaby··on Nerd: A language for LLMs, not humans
Perhaps they are being more successful in their use of llm's than you are?
alienbaby··on Asking Gemini 3 to generate Brainfuck code results in an infinite loop
``sometimes, it even happens with [antigravity]``

Isn't this a problem with the agent loop / structure, rather than the llm, in that case?

The ide doesn't affect the models results, just what is done with those results?

alienbaby··on FFmpeg has issued a DMCA takedown on GitHub
Llm's do not verbatim disgorge chunks of the code they were trained on.
alienbaby··on Scaling LLMs to Larger Codebases
I'm curious in what kinda if situations you are seeing the model the do opposite of your intention consistently where the instructions were not complex. Do you have any examples?
alienbaby··on Structured outputs create false confidence
I've wondered if it's because structured outputs rely on visual cues to impart meaning, and turning them into token streams looses that spatial structure.
alienbaby··on Engineering dogmas it's time to retire
Exactly what I thought and why I checked the comments , an lo and behold it's not just me..
alienbaby··on The State of AI Coding Report 2025
I actually ended up enjoying reading the cards after the charts more than I did reading the charts, but the charts were really interesting too.
alienbaby··on If AI replaces workers, should it also pay taxes?
If it can consume public resources and has a vote, maybe?
alienbaby··on Programmers and software developers lost the plot on naming their tools
I have agreed with this for at least a decade. Name your things in a way related to what they do.

What does chef do? Garden? Pig? Burp?

Nonsense.

alienbaby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
This will be fine, until you can't tell the difference and they forgo the 'i asked'
alienbaby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
This will be fine, until You can't tell the difference and people forgo the 'i asked' part.
alienbaby··on IBM to acquire Confluent
There are good people in IBM. But they don't have the resources behind them anymore. Look at the market cap of ms, Amazon. Google, meta et al, compared to IBM.
alienbaby··on IBM to acquire Confluent
They gave up on watson about 18 months before llm's popped up, and they have simply just not got enough cash on hand to compete. While the big boys grew fantastically bigger over the past 15 years as cloud happened ibm fumbled time after time and shrank ever smaller, and is now desperately hoping it can stay relevant. but in the end they just haven't got the resources to compete on that stage anymore.
alienbaby··on The AI Backlash Is Here: Why Public Patience with Tech Giants Is Running Out
Ai is a lot more than ai generated media.
alienbaby··on Are we repeating the telecoms crash with AI datacenters?
Did you see the reply from the author to similar statements?
alienbaby··on Are we repeating the telecoms crash with AI datacenters?
You guys make me laugh.
alienbaby··on Google Antigravity just deleted the contents of whole drive
This is speculation currently, the actual reason has not been determined
alienbaby··on We ran over 600 image generations to compare AI image models
Interesting experiment, though I'm not certain quite how the models are usefully compared.
alienbaby··on Vibe Code Warning – A personal casestudy
This was my exact first experience trying to build anything of significant size.

Several projects later, I can work with the AI now to produce several thousand lines of code, I understand it, it is what I asked for, has the architecture I wanted, is not bloated and is not buggy.

Spend time planning, figuring out the architecture you want, refining, breaking things down into smaller implementable features with implementation plans for each feature. Review these things aggressively. Make sure they align with your expectations.

Then get it to start writing code. Writing tests for everything. Include detailed runtime logging. Read what it produces, understand it and redo it if it wasn't what you expected. Your experience will be vastly superior to that first attempt.

alienbaby··on OpenAI may not use lyrics without license, German court rules
Can't they just ask for copies of the lyrics they are not allowed to use and s/lyrics//g the training set? I imagine the volume of text that will be removed would be relatively miniscule.
alienbaby··on Vodafone Germany is changing the open internet, one peering connection at a time
it sounded to me like an AI generated article covering it's ass, or at least written by someone who did naught but AI generated research as their own 'research'.
alienbaby··on I’m worried that they put co-pilot in Excel
Using ai does not absolve you from the responsibility of doing it correctly. If you use ai, then you better have the skills to have done the job yourself, and so have the ability to check the AI did things correctly.

You can save time still, but perhaps not as much as you think, because you need to check the ai's work thoroughly.

alienbaby··on We are building AI slaves. Alignment through control will fail
Until agi can sit there and ponder its own existence of is own violition and has the means to act upon it's conclusions, I'm not too worried.
alienbaby··on Uv is the best thing to happen to the Python ecosystem in a decade
Can I just start using python if I've already got a bunch of projects manage with venv / pyenv / virtualenv ( and tbh I've kinda got into a confused mess with all these venv things, and at this point just hope they all keep working...)
alienbaby··on World Simulator: Create and Play Interactive AI Worlds
I'm not a fan of being asked for payment before I know what I'm getting
alienbaby··on Show HN: I built an 8-bit CPU simulator in Python from scratch
Nice. I wrote something exactly like this to simulate a CPU with an instruction set and registers that were extended beyond general purpose instructions to include op codes to read board state and generate moves for a game of go. That then became the core of a system setup to use genetic algorithms to try and 'breed' go playing programs.

It didn't produce anything close to a competent go playing program, but it did get to the point it would play legal moves, which considering I started it with a purely randomly generated population of programs, it had zero built in knowledge of the rules of go, and had it playing against a well known open source go playing program to assess fitness of a given pop, I was quite pleased with it.

This was around 10+ years ago, just as Google made alphago.

alienbaby··on Programming with Less Than Nothing
ok, but if you did this in an inteview I was giving I would say "clever, but you didn't get the job". Mainly because you missed the point of the interview.

We have a guy who joined recently who constantly tries to be as clever as possible when writing his code. He ignores established patterns and conventions because he knows better. He does some cool stuff. Really cool stuff.

He's so far bounced thorugh 3 different teams, I don't think he'll be with us long.

← PreviousPage 8 of 10Next →