HNHacker News
TopNewBestAskShowJobs

baddash

330 karma · joined April 13, 2018

mclaren212@gmail.com
submissionscomments
baddash··on Toxic experts (2017)
also known as Douchebags
baddash··on Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer and Backdoor
litellm in the news again
baddash··on Five months treating bugs like patients and coding agents like a medical team
i think role-play and utilizing the full power of language, stories, character, and narrative will unlock very sophisticated use-cases and in general a new dimension to agentic systems much in the way you're describing.

probably what will work best in the future is specific training or fine-tuning against curated datasets of narrative fiction and/or texts in general? not really sure.

baddash··on OpenAI "rogue" agent activities found on Wikimedia projects
wtf is wrong with openai?
baddash··on I don't want the details
i don't want to sound like a douchebag but isn't figuring out what went wrong and how to prevent next time kind of an obvious goal
baddash··on The revolt of the reader
is this... an ad
baddash··on Why do I lose my passion and want to do nothing?
how are we supposed to answer that? we don't know anything about you lol. you gotta give me more info, like, results for what? when you're coding? what are you working on? is it driven by yourself or is it for your job? help me help you.
baddash··on Microduck
thought this said something else at first
baddash··on [dead]
as soon as i saw "silently" i knew who actually wrote this
baddash··on The End of an Athlon
AFLAC!?
baddash··on Assembly Hall of Shame
just curious, how much do these actually discover useful practices or pitfalls, on top of just being for fun?
baddash··on Show HN: Nightcrawler – A local AI pentesting agent running on a smartphone
little bit unrelated, but I watched the IG video and I thought the visual design of the app was cool af! what inspired the style?
baddash··on Our position on open-weights models
maybe instead of worrying that people on the internet will be good at coding, we could start writing memory safe apis. almost all cves are fixed by using rust
baddash··on If coding has been solved, why does software keep getting worse?
I don't get this post. It says software is getting worse, and then... gives a handful of anecdotal evidence. That could have been done at any point in the life of the software industry, including in the pre-agentic era. So the assertion behind the post doesn't really have any weight to it. Is there any actual, respectable evidence that software is actually getting worse? Also, what would worse even mean really? More buggy? Less reliable? Less creative, flexible?
baddash··on OpenPrinter
is it better than a Brother printer, cause i've had one for like a decade and it's the shit
baddash··on Show HN: I made a heatmap of 3400 VCs who are open to cold emails
xD i think it's a cool tool though
baddash··on Show HN: I made a heatmap of 3400 VCs who are open to cold emails
all the chicago ones are swimming out in lake michigan
baddash··on Tokenmaxxing is dead, long live tokenmaxxing
it's a huge oversimplification imo. it reminds me of someone worshipping LOC: more = better
baddash··on Previewing GPT‑5.6 Sol: a next-generation model
how much does your setup cost you? just curious
baddash··on The Coming Loop
title describes my life in a nutshell
baddash··on My 1992 view of the problems of computer programming in 1992
what do you think of it?
baddash··on Identity verification on Claude
i think claude is going to become the AI of the US government/public sector. if it isn't already
baddash··on Why thinking out loud with someone beats thinking alone
perhaps it is time to resurrect Duckly queue Frankenstein music and thunder in background
baddash··on Ask HN: What are you working on? (June 2026)
why are digital identities becoming more prominent?
baddash··on Ask HN: How long have you been looking for a job?
do you mind sharing the name of the company? I could use some help in the search too. my email is on my profile if you prefer that
baddash··on Ask HN: What are you working on? (June 2026)
i haven't finished either, but once i do i can send you a message or something. my email is on my profile if you wanna exchange contact info
baddash··on Ask HN: What are you working on? (June 2026)
i'm working on something similar, not a full agent harness but an agentic workflow app so i can learn too. if you're interested in sharing it would be awesome to take a look. i can share my project too!
baddash··on Introducing alint
cool, sorry if i missed this but what initially inspired you to make alint?
baddash··on You weren't meant to have a boss (2008)
Look into Haier's RenDanHeYi philosophy. One of my ambitions is to adopt that model when I start a company, and I think it is awesome and the future.

BTW, seems like we think similarly regarding this. Wanna exchange contact info? my email is mclaren212@gmail.com if you're interested in connecting

baddash··on AI Agent Guidelines for CS336 at Stanford
Not from simply looking at the answer. From knowing the answer and reverse-engineering or understanding how to arrive at that answer in the first place. It's not always the best way of learning, but it definitely is a great way to learn if you care to actually understand why it is the answer and how you would have arrived at it.

> Your suggestion means we're no longer coddling/shielding students, but we also aren't actively helping them, are we?

My suggestion is just the former, it doesn't imply the latter.

Page 1 of 5Next →