Hacker News: not_ai

New comment by not_ai in "City Learns Flock Accessed Cameras in Children's Gymnastics Room as a Sales Demo"

not_ai — Fri, 01 May 2026 23:14:29 +0000

Exactly. If anything they will want to target those schools more. They want to be famous, they idolize each other.

New comment by not_ai in "HashiCorp co-founder says GitHub 'no longer a place for serious work'"

not_ai — Wed, 29 Apr 2026 12:54:36 +0000

At one point it was also used as signaling that a company was “modern.”

New comment by not_ai in "Claude Opus 4.7"

not_ai — Thu, 16 Apr 2026 14:42:12 +0000

Oh look it was too powerful to release, now it’s just a matter of safeguards.

This story sounds a lot like GPT2.

New comment by not_ai in "Model-Based Testing for Dungeons & Dragons"

not_ai — Fri, 10 Apr 2026 12:13:46 +0000

I think this is fantastic. I recently started playing DnD with a local group and can’t wait to dive into this to better understand the mechanics.

New comment by not_ai in "Agent-to-agent pair programming"

not_ai — Fri, 27 Mar 2026 11:27:40 +0000

And expensive, exactly the way a pay per use product would push its customers…

“It’s not working well enough!” We tell them. They respond with “Have you tried using it more?”

New comment by not_ai in "Claude now creates interactive charts, diagrams and visualizations"

not_ai — Thu, 12 Mar 2026 20:37:20 +0000

I have a very different experience. Claude code tui is the worst tui I have ever used. How is it possible that an inactive tui regularly eats 8gb of ram, has freezing issues and rendering issues?

If I wasn’t forced to use it I wouldn’t as there are better options available.

New comment by not_ai in "Tech employment now significantly worse than the 2008 or 2020 recessions"

not_ai — Fri, 06 Mar 2026 21:58:17 +0000

Thanks for sharing this is the first I’ve seen this. I wish they had expanded on exactly what mid-level might be missing rather then just saying “fundamentals” and “practical intuition”

New comment by not_ai in "Father claims Google's AI product fuelled son's delusional spiral"

not_ai — Wed, 04 Mar 2026 20:53:02 +0000

Preferably the C-Suite.

New comment by not_ai in "Gemini 3.1 Pro"

not_ai — Thu, 19 Feb 2026 23:38:50 +0000

After spending all that money and firing a bunch of people? Is the new group doing anything at this point?

New comment by not_ai in "TikTok's 'addictive design' found to be illegal in Europe"

not_ai — Fri, 06 Feb 2026 21:32:58 +0000

I’m happy to see that Flink is in this stack, I wish that Pulsar was as well instead of Kafka.

New comment by not_ai in "Todd C. Miller – Sudo maintainer for over 30 years"

not_ai — Tue, 03 Feb 2026 00:13:30 +0000

The monthly releases seem to indicate otherwise.

New comment by not_ai in "MaliciousCorgi: AI Extensions send your code to China"

not_ai — Mon, 02 Feb 2026 14:07:56 +0000

At the company I work for they locked down installing extensions through the marketplace. Some are available but most are not and there is a process to get them reviews and approved. You might be able to side load them still but I haven’t cared enough to want to try.

They did the same with Chrome extensions.

New comment by not_ai in "Tesla ending Models S and X production"

not_ai — Thu, 29 Jan 2026 14:45:29 +0000

I did not know this and explains why I see so many teslas with their blinkers on and not maneuvering despite having ample room and time. Ultimately this behavior makes them unsafe for their occupants as well as others around them.

Cars only work because we can predict driver behavior, if they break that prediction that’s when bad things are likely to happen…

Lately I’ve started to ignore Tesla blinker.

New comment by not_ai in "Slop is everywhere for those with eyes to see"

not_ai — Fri, 16 Jan 2026 21:18:51 +0000

Not really, it’s just the interface OpenAI gave for creating short videos with their AI. They push people to it hoping for engagement, but it’s not the sole reason people go — unlike TikTok.

New comment by not_ai in "Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone"

not_ai — Wed, 07 Jan 2026 00:06:01 +0000

I’ve only used web codex version but everything about it was slower than what’s described here, broken flows, more rate limited and impossible to “human in the loop” before a PR.

New comment by not_ai in "Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone"

not_ai — Tue, 06 Jan 2026 23:02:22 +0000

This can be done not just with Claude but also with codex and gemeni cli. Well technically anything that has a cli interface.

I run both gemeni (fee) and codex (paid), with tmux thrown in to switch between phone and laptop. Laptop runs vscode with ssh to my server but I could also use the web version of vscode.

New comment by not_ai in "Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone"

not_ai — Tue, 06 Jan 2026 22:51:18 +0000

I just have it send me a push notification.

New comment by not_ai in "The "confident idiot" problem: Why AI needs hard rules, not vibe checks"

not_ai — Mon, 08 Dec 2025 14:14:08 +0000

I didn't have the words to articulate some of my frustrations, but I think you summed it up nicely.

For example, there's been many times when they take it too literally instead of looking at the totality of the context and what was written. I'm not an LLM, so I don't have perfect grasp on every vocab term for every domain and it feels especially pandering when they repeat back the wrong word but put it in quotes or bold instead of simply asking if I meant something else.

New comment by not_ai in "Ask HN: How is you and your team are using AI?"

not_ai — Sun, 07 Dec 2025 14:44:41 +0000

There is no alignment, there is no sharing of rule files or other instructions. These are tools no different then an ide which people are also free to choose so why would we?

Also rule files and other "memory sharing" are crutches. If it's that important just put it in your readme or other documentation and the LLM can get the context from that just like your teammates.

Plus isn't it a little silly this extremely well capitalized companies can't figure out how to get an LLM to follow a readme effectively and instead wave it away by saying you need to now maintain yet another thing?