HNHacker News
TopNewBestAskShowJobs

PeterStuer

11,106 karma · joined October 5, 2015

submissionscomments
PeterStuer··on I think I have LLM burnout
"My main project right now is to establish a framework for large-scale, unsupervised code generation in our codebase... sifting through the unsupervised agent’s (Qwen’s) output"

Ouch. I love my local AI setup with Qwen, but that is a mismatch right there. That model is not the right match for that project. It's like trying to develop a major software solution by just throwing in hundreds of fresh junior programmers and have them spew out random code bits, while what you needed is a good PM, a great architect and a handfull of senior engineers. Might as well pack it in for a year until your model has grown into the ability for those rolls. There is a reason why Opus 4.6 and now Fable dramatically changed the SWE capabilities, and IMHO Qwen is not there yet.

PeterStuer··on How to Build a Minimal ZFS NAS Without Synology, QNAP, TrueNAS (2024)
Rather than 'plain' debian you can put it on Proxmox, and enjoy the bliss of Proxmox Backup Server.
PeterStuer··on Claude, please stop trying to memorize random crap
I must admit lingering long since retired 'memories' are currently one of the biggest pitfalls of the setup. Wiping all 'memory.md' often leads to better sustain.
PeterStuer··on Opening up 'Zero-Knowledge Proof' technology to promote privacy in age assurance
Have you read the DSA?
PeterStuer··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
Sure we can nitpick semantics, but how would you describe the evolution in GenAI SWE capability over the last 18 months?
PeterStuer··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
100% agreed, and I do experiment, but it is atm just a question of where to put the effort first.
PeterStuer··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
My development platform of choice is Opus 4.8 --effort max. My 'in production' general model just switched from GPT-4o to GPT-5.2. I probably should test local inference for that part (some translation/knowledge extraction/summerization) next but it has not made it to the top of the priority list yet, even though 3 other small specialized task models in the app already run on prem.
PeterStuer··on Fable 5 is Back
Remember the Clipper Chip back in 1993 because personal computing was considered too dangerous a technologie to be accesible un-controlled/suprvised to the general public?
PeterStuer··on Fable 5 is Back
So a model named 'Fable 5' is "back". Both excited, as the previous Fable 5 I had access to for just 3 days was fantastic, and anxious as (yes, in my 1 person anecdote) the model refered to as 'Opus 4.8' was stealth nerfed over the last 2 weeks to a degree I had not experienced since the massive nerfs back in the GPT-3.x days. Fingers crossed.
PeterStuer··on Opening up 'Zero-Knowledge Proof' technology to promote privacy in age assurance
Will they not just argue that you could share the assertion, and hence we need a 'trusted' verfication point to establish it is actually you in posession of the zkp token, right now. So turn on that smartphone camera right now and obediently follow our biometric verfication instructions ...
PeterStuer··on Opening up 'Zero-Knowledge Proof' technology to promote privacy in age assurance
"We" are building 1984 to make sure "We" stay in power of our EU Animal Farm.
PeterStuer··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
I hear that often, but what does that even mean? I am a great proponent of open weights models. I do believe they are the only reason we have not stagnated into a collusion of halting (public) model releases.

But exactly which point in time is z.ai compared to claude.ai? Consistently bring "6 months behind" in an exponentially acellerating evolution means the gap is growing exponentially wider, not constant.

PeterStuer··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
In my experience: anything of open-ended complexity (software development, research, product design, ...) benefits from wathever the frontier can offer. 95% of Line of Business automation and workflows can be handled by even a reasonably small open weights generalist model flanked by a few even smaller specialized models. Yes, designing such a setup takes more knowledge and work dan just chucking it all over the api with prompts. But that is how I can run a system here for <$30/month vs >$1.000 month. As an added bonus, no model server can shut me down at the drop of a hat.
PeterStuer··on Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5
For real production I find the switching cost is not as trivial as you portray. Even going to a new model version in the same model family, say GPT-4o to GPT-5.2, a transition I just finished on a not too complicated application, requires extensive retesting and tweaking of prompts, guardrails and parameters.
PeterStuer··on Claude Sonnet 5
Anyone else feel like Opus 4.8 got significantly dumber over the last 2 weeks?
PeterStuer··on GLM 5.2 beats Claude in our benchmarks
Because it truly makes a difference. Opus 4.8 was great until we experienced Fable 5.

And post Fable retraction, I am now most certaily noticing Opus being 'dumber' also.

Open Weights are good. Not (yet) as good as leading closed models. Unfortunatly they will be declared 'illegal' any day now, and I unfortunately do not see myself able to run GML 5.2 in my basement homelab any time soon.

PeterStuer··on Microsoft Needs Windows Lite
So no juicy 'telemetry' data for profiling, recurring revenue service tie-ins, advertizing revenue deals nor hefty 'store' margins?

Somehow I don't see this happening.

PeterStuer··on Qwen 3.6 27B is the sweet spot for local development
No laptop is thermally designed to handle sustained high workloads. The whole point of a laptop is to keep it thin, quiet and light, the exact opposite of what cooling needs.
PeterStuer··on Qwen 3.6 27B is the sweet spot for local development
The M3 with 512GB is currently sitting at around 30K, used. You can extrapolate from there.
PeterStuer··on Qwen 3.6 27B is the sweet spot for local development
Been running it on a 9950x3D with 96GB and a 4090. Speedwise it is fine. Bit while not completely useless, for software development it is unsurprisingly a dramatic downgrade from the Opus I use as my daily driver.
PeterStuer··on Turn your site into a place people can bump into each other
... and run head first into totalitarian 'chat control' regulation all around the globe.
PeterStuer··on Austria Lobbies EU to Host Anthropic After US Access Curbs
So how do these people propose to protect all involved after they defy CFIUS?
PeterStuer··on Reducing tick density along recreational trails in Ottawa, Canada
Wearing appropriate clothing for walking grassy trails is 95% of the solution. Decent walking boots, trousers in socks and a long sleeved shirt goes a very long way.

And no, it does not have to be too warm if you use an appropriate light and wicking fabric.

PeterStuer··on AMD Strix Halo RDMA Cluster Setup Guide
The 512GB Mac Studio is going for around 30K used.
PeterStuer··on Extreme Heat conference cancelled due to extreme heat warning
People 'thrived', not just 'survived' in e.g. the Mediterranean long before AC.

I speculate the restriction on AC in that conference room is because it is a unique historic location they want to preserve, not some ideological anti-AC dogma.

PeterStuer··on Political bias in AI: Where the AI models stand
Not at all.
PeterStuer··on MicroVMs: Run isolated sandboxes with full lifecycle control
Setting up your own is not that hard and if you bought some compute before the Altman squeeze, very cheap.
PeterStuer··on Why current LLM costs are not sustainable
Same for me, comfortable with a single Max sub, launching "claude --effort max" with Opus 4.8 (alas poor Fable, please come back!).

But try running Claude Opus at API prices through a 'clever' RAG based intermediate system 'managing' a 2024-era context size window completely unaligned with 2026 frontier model tool use expectations, that results in 100% cache miss and content coherency destruction on every single interaction. There's your typical 'Enterprise Agreement' GenAI setup.

I only really discovered this when trying to find out how my Enterprise friends' AI experiences were so completely opposite from my own successes as I could not believe how poor their results were even though on the surface it looked like we were using the same model, and I know they aren't 'bad' software engineers and developers.

PeterStuer··on Political bias in AI: Where the AI models stand
The concepts (left/right. authoritarian/libertarian) seem to fluid to help sensemaking. Stances that would have been mainstream left (democrat US) just a few years ago are now labeled MAGA (US) or 'extreme right' (EU). And nobody seems to believe their own side is 'authoritarian', but everyone that disagrees with them is a literal ...
PeterStuer··on Hey Nico, you didn't vibe code your data room but stole it from Papermark
If you are convinced this is a winner takes all race to ASI, and ASI results in absolute world dominance, then of course you are never going to feel restricted by current laws, especially not simple IP rules. Because the only way to make 100% sure you lose is not to play.
← PreviousPage 6 of 34Next →