HNHacker News
TopNewBestAskShowJobs

blurbleblurble

5,617 karma · joined November 14, 2015

submissionscomments
blurbleblurble··on Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
Really nice intuition, thank you.
blurbleblurble··on Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
In this blog post I'm reading their call for "control flow" as a generalization of exactly what your work illustrates so nicely.

The blog post doesn't say to me "we need to start encoding specifically opinionated conditional branching statements that guide the model" rather I'm hearing a call to realize the broader principles of control flow itself relevant for composing programs with LLMs.

I think your work "nudges" us in that direction.

blurbleblurble··on Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
Deja vu from the other week https://news.ycombinator.com/item?id=48051562
blurbleblurble··on Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
Nice explanation, thank you.

So basically the kind of thing I'd usually be doing manually with small models, over and over again, you just automate that nudging and off they go.

Sometimes LLMs have seemed to me like "computer programs with inertia" and in that frame what your tool does is identify and reduce friction at key points so the wheels can keep spinning.

blurbleblurble··on Elon Musk has lost his lawsuit against Sam Altman and OpenAI
I don't believe in racial essentialism myself but I know someone who does

*ducks to dodge downvotes for not only making a bad dad joke but a political one*

blurbleblurble··on The AI water issue is fake
Listen, I really like LLMs and diffusion models and machine learning and all this stuff, and I want to see it happen in a just and sustainable way. "AI" doesn't necessitate extreme waste. If anything, reasonable policy constraints would push "AI" to be even better.
blurbleblurble··on WHO declares Ebola outbreak a global health emergency
The cynic in me sees this kind of outbreak as exactly the intention of the current US administration in gutting CDC funding and leaving the WHO.

It's misanthropic behavior, fueled by their big bunch of various essentialist inferiority/superiority complexes.

blurbleblurble··on Open Source Resistance: keep OSS alive on company time
I'm in the US and have made a living writing open source for almost 10 years now, through ups and downs, but it's worked out.
blurbleblurble··on Open Source Resistance: keep OSS alive on company time
It's also just good business sense. Companies that promote collaboration via open source are promoting the ecosystem that feeds their business.
blurbleblurble··on Open Source Resistance: keep OSS alive on company time
I wouldn't take a job where the employer wasnt publishing permissively licensed code for all but the production bits. It's demoralizing for me and would stress my soul to the brink. I'd rather be broke.
blurbleblurble··on Komai: a fine Matrix chat app you can get to love
People are afraid and taking it out on others
blurbleblurble··on Computer Use is 45x more expensive than structured APIs
"AI" is a made up hype thing. It's just computers and computer programs. For real!
blurbleblurble··on AI didn't delete your database, you did
Maybe the reason this is so controversial is that people have stopped thinking about "AI" as a bunch of software, just like any other software. If that's you, stop while you still can, you've swallowed a nasty hook and your agency is on the line.
blurbleblurble··on Google Chrome silently installs a 4 GB AI model on your device without consent
This is total flamebait
blurbleblurble··on White House Considers Vetting A.I. Models Before They Are Released
For those among us who voted for this administration: what's the plan? More doubling down?
blurbleblurble··on White House Considers Vetting A.I. Models Before They Are Released
Why not all that and more?
blurbleblurble··on Why Almost Everyone Loses–Except a Few Sharks–On Prediction Markets
I don't see how regulating authorities could truly decipher the distinction between incompetence and pyramid hype fraud / shell company money laundering schemes at scale.
blurbleblurble··on Why Almost Everyone Loses–Except a Few Sharks–On Prediction Markets
The twisted thing about it is that the surface logic of putting a hit on someone via prediction market involves betting that they'll stay alive. How innocuous looking.
blurbleblurble··on Why Almost Everyone Loses–Except a Few Sharks–On Prediction Markets
What's the difference between penny stocks and prediction markets?
blurbleblurble··on How Mark Klein told the EFF about Room 641A [book excerpt]
They're sustainable but require major cultural revolution to keep up.
blurbleblurble··on Granite 4.1: IBM's 8B Model Matching 32B MoE
Codex cli is open source
blurbleblurble··on Granite 4.1: IBM's 8B Model Matching 32B MoE
I agree but would add that gemma 4 is really nice at vibing though in ways qwen 3.6 could never.

Maybe it could be fun to hook them up via a2a protocol as left and right brain agents operating in tandem.

blurbleblurble··on Claude.ai and API Unavailable
More fuel to get 27b running
blurbleblurble··on Claude for Creative Work
People are guzzling the amygdala control juice these days
blurbleblurble··on Vibe Coding Will Break Your Company
"This is what vibe coding is about to expose across businesses. The companies that think the story is about software are going to lose to the companies that understand the story is about judgment."
blurbleblurble··on GitHub is having issues now
Maybe that's why I couldn't filter my stars by language
blurbleblurble··on Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview
My sense is that we're at a tipping point where instruction following is getting good enough to disrupt these old habits
blurbleblurble··on Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview
Yes, I've tried this passive approach too and didn't dig much further after that. I thought maybe they'd figured out something more intentional in the prompting to enable these kinds of approaches.
blurbleblurble··on Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview
Did you consider incorporating ast-grep or gritql?

Congratulations, great work.

blurbleblurble··on An AI agent deleted our production database. The agent's confession is below
The author posted their own confession right here: https://pbs.twimg.com/profile_banners/591273520/1719711719/1...
← PreviousPage 4 of 34Next →