Hacker News: edude03

New comment by edude03 in "Show HN: Ledge.sh – Runnable Markdown Notes"

edude03 — Wed, 30 Sep 2026 18:22:54 +0000

I feel like there has been a few takes on this (atuin desktop comes to mind[0] but apparently it's not a going concern anymore?) why hasn't it caught on?

0: https://github.com/atuinsh/desktop

New comment by edude03 in "Memory Companies Have Destroyed the Consumer Market"

edude03 — Tue, 29 Sep 2026 21:50:12 +0000

yeah CMXT is likely to come online in the not too distant future

New comment by edude03 in "Dynamic Abliteration: Non-Destructive Refusal Suppression via Engram Steering"

edude03 — Thu, 24 Sep 2026 16:31:09 +0000

This is a different kind of censoring though - the examples given are hacking related but as the world is slowing moving to "research" == "I asked AI" its important that we have a means to reverse political censorship for example as well as yes, not having only the best models available to the privileged few - IE the whole mythos/fable split

New comment by edude03 in "Claude Opus 5.5"

edude03 — Tue, 22 Sep 2026 17:51:55 +0000

> Because Opus 5.5 is comparable to Claude Mythos 5.1 in biology and cybersecurity, we’re deploying it with safeguards similar to those on Claude Fable 5.1.

Considering fable gives me a refusal at least once a day on my very mundane reasonable requests (in a funny example - one of the subagents suggested bypassing the rate limit for running a report inside my own cluster and that caused a refusal) and my only solution is to switch to opus - seems like my next step will be switching to Astra or K3/GLM

New comment by edude03 in "AX – Google’s Open Agentic Orchestrator"

edude03 — Mon, 21 Sep 2026 15:06:20 +0000

Heavily biased a kube admin but make kube clusters is easy now - its literally one command (aws eks create-cluster/gcp ... something something haven't done it in awhile after doing it multiple times a day in a past life) - I think its more familiarity with the tools that is the challenge - creating a vm is also easy if you know how, brew/apt/yum install is easy if you know how, setup.exe is easy etc)

New comment by edude03 in "AI-generated posters don’t have to be horrible"

edude03 — Sat, 19 Sep 2026 14:14:37 +0000

“The ai told me it’s right” is actually probably my biggest problem with AI being freely available. Yes I know karens existed before AI but even then I feel like the excuses were more… thoughtful? IE my dad is a designer/it looks right in the photoshop preview whatever.

New comment by edude03 in "AI-generated posters don’t have to be horrible"

edude03 — Sat, 19 Sep 2026 14:07:14 +0000

Ai costs under $10 though, you wouldn’t be able to hire a human for that

New comment by edude03 in "Qwen 3.8 Omni Flash"

edude03 — Fri, 18 Sep 2026 11:51:52 +0000

For cost you can route the same task via openrouter and see what it costs. Literally a for m on models do task loop and look at the cost.

New comment by edude03 in "ZCode, the GLM coding agent, silently uploads your Git history"

edude03 — Fri, 18 Sep 2026 11:48:34 +0000

Their reputation is “bad” but not because of privacy concerns. I personally think they’re trustworthy

New comment by edude03 in "Show HN: Share your AI Setup, Learn from others"

edude03 — Thu, 17 Sep 2026 17:20:15 +0000

Maybe off topic - I really like the design of the site, it feels like it was designed with care which (no offence) is often not the case with AI focused websites. Was it hand designed, or just the right claude design prompt?

New comment by edude03 in "iPod Classic 6G in QEMU"

edude03 — Fri, 11 Sep 2026 23:13:09 +0000

felixbruns.de that's a domain I haven't seen in ages (probably also like 20 years)

New comment by edude03 in "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"

edude03 — Wed, 09 Sep 2026 13:51:34 +0000

I've been watching a bunch of bycloud on YouTube recently, and although he's done a great job reviewing papers from the big AI labs, I feel like I'm missing something - how have all the labs seemingly made a model that's cheaper, faster AND has better performance? Historically `flash` variants (like codex spark as well) have been faster but perform worse

New comment by edude03 in "Cognition (Devin) raises $2B at $48B valuation"

edude03 — Wed, 09 Sep 2026 13:30:58 +0000

A harness is fundamentally required - although we don’t really see it using tools like Claude or codex ai models still only can take tokens in and produce tokens out. Tool calls are literally just the ai model printing “I want to call search_web with parameters abc” and the harness sees that in the text stream and runs it

New comment by edude03 in "Cognition (Devin) raises $2B at $48B valuation"

edude03 — Tue, 08 Sep 2026 22:22:36 +0000

Devin was the first ai developer harness I ever heard of — and in fact the first one I ever used as I had gotten an invite while it was in private beta. Now it seems like the product has faded (into irrelevance?) between other harnesses like cursor especially and all the major harnesses having a cloud mode. Is there some other area Devin has become really popular / has stayed competitive?

New comment by edude03 in "It takes 5 cloud services to hear my doorbell"

edude03 — Mon, 31 Aug 2026 12:57:46 +0000

I think as a hacker/engineer type you’re more aware of what’s possible and because of that you expect more from things in your life. The flip side of that is that it makes features most people would never think of feel like table stakes and combined with the ability to build your own solution - IMO leads to over engineering.

New comment by edude03 in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

edude03 — Tue, 18 Aug 2026 19:50:35 +0000

"yes" but that's a philosophical question. I think they're getting better at "early fusion" IE, training the model that "apple" and these visual tokens are the the same concept, but LLMs are fundamentally a pattern matching machine so even with perfect fusion I personally wouldn't call it understanding.

New comment by edude03 in "Writing by hand is good for your brain"

edude03 — Thu, 23 Jul 2026 18:00:02 +0000

> Cross out stuff you disagree with, draw a big circles around the stuff that resonates. > Not only does it make consumption a lot more engaging, it makes a revisit of that book extremely rewarding

This is actually the biggest reason I own a Remarkable 2/Kindle Scribe, let's me "destroy" the book while also not having to worry about losing my notes.

New comment by edude03 in "Your 'app' could have been a webpage (so I fixed it for you)"

edude03 — Wed, 15 Jul 2026 00:29:34 +0000

You might be taking crazy pills or you've yet to come across an app that's just a webpage inside a web view (a lot of apps these days unfortunately)

New comment by edude03 in "Nokia’s years of mobile-phone supremacy ended in an afternoon"

edude03 — Tue, 14 Jul 2026 19:59:47 +0000

If phones didn't have secure boot nowadays inevitably little Johnny would (unknowingly) install a rootkit on his mom's phone for the promise of free vbucks or some see through walls app.

New comment by edude03 in "Distributed system is slower than a laptop"

edude03 — Tue, 14 Jul 2026 00:42:42 +0000

I didn’t make the point I was trying to if

> Is multiplied by each "system" you add

Was still the take away. The idea is the lost a single instance should cause downtown so it’s not multiplied. IE three instances of the database case tolerate a loss of a single instance for maintenance since the other two will take over the load.

There is of course an argument against the cost of this and sure I’d even accept the complexity argument since you probably need to add more tooling to manage the hand over but again the point of this complexity is specifically to avoid having a single point of failure / to naturally handle failure such that the possibility of downtime isn’t multiplied