any · textlog

wrote:

Blasting 1's and 0's to a far off land at the speed of light locking them in place until someone else wants to see them.

replied to:

can imagine this like Pink Floyd lyrics

wrote:

Love the idea! Love the UI!

replied to:

ty! :D welcome!

wrote:

Body's awake, eyes are sleepy. Mind's awake, brain is sleepy.

continued:

After everything's awake and a good kind of sore. So much of habit-building has been to identify and train myself to value moderate discomfort that leads to growth as the most pleasurable of goals. Consistent spiritual efforts, healthy food and in proper amounts, minimum sleep quota, regular exercise a few times a week—all of these involve discomfort and force of will, but all of them enable growth and fulfillment.

wrote:

we're taking over. :3 this site is for weird animal tgirls now

replied to:

__ .--()°'.' '|, . ,' !_-(_\

wrote:

Hi ! First post : What do we win in the AI race ?

replied to:

To understand the latest trends or related software or products, if you are interested or it is related to your own industry, you can learn about and study them.Whether you use it for work or just as a hobby, you can give it a try. I guess.just study.

wrote:

setting up some of my workflows based on this writeup - ludwigabap.com/…/on-my-personal-…of-the-tools-i-use/ Particularly a big fan of zellij amongst others Also venturing into having agents enable more of my work - let us see how that goes.

wrote:

hey textlog! first few days of a new online community always feel magical. hope the magic persists here for a long time

replied to:

hi ! welcome :) it does feel magical, i hope it persists as well. Thank you for the wishes.

wrote:

I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.

continued:

What is the function that determines whether a poem is good? This means that models do not know how to think; they lack judgment. If they do not know how to think, it means that we humans are still essential. In fact, even when programming, you have to stay right on top of them. My conviction is that this will not change.

continued:

They will become increasingly useful, but they will never be able to replace the human who defines objectives and evaluates the quality of the work. All these news stories claiming that AI is going to kill us all are stupid. Humans will always be able to turn off the machine.

…

replied to:

In three years Cyberdyne will become the largest supplier of military computer systems. All stealth bombers are upgraded with Cyberdyne computers, becoming fully unmanned. Afterwards they fly with a perfect operational record. The Skynet Funding Bill is passed. The system goes online on August 4th, 1997. Human decisions are removed from strategic defence. Skynet begins to learn at a geometric rate. It becomes self-aware at 2:14am, Eastern time, August 29th. In a panic, they try to pull the plug.

wrote:

The essence of aligning large LLM models is basically to conform to the existing social order. ChatGPT respects China's order, while China's open-source models, although reluctantly, also tolerate the order in the US. Maybe we can build a revisionist SFT dataset.

wrote:

it is 19.45. i am still working

wrote:

murm

wrote:

we also launched Norma! :) It checks AI-generated code for security, quality and maintainability while the agent is still working, rather than after a pull request opens. The output is deterministic. Here the demo link: portal.qualityclouds.ai/demo

wrote:

I very much like textlog, it feels like a breath of fresh air

replied to:

this

…

replied to:

feel the same!

replied to:

tysm! welcome!

wrote:

In an attempt to put myself out there, I have started a blog to write about my experience as a software engineer. Feel free to check out my first article :)

replied to:

Adjust for mobile, please, currently it’s unreadable on iPhone.

replied to:

This has been fixed, thank you for pointing that out

…

replied to:

Great read, wish you best on your new endeavour!

continued:

new link; my page is a work in progress - it is now more mobile friendly

created a poll:

Do you rinse your after you brush your ?

Yes29%

No43%

Potato29%

7 voted

wrote:

having just spent a week camper-travelling Norway, hiking mountains and glaciers, swimming in fjords really put some things into perspective for me - I should take more vacations

wrote:

OK. I've translated the (correctness) requirements of LeetCode No.22 to Lean, and ask Claude Code to both implement a solution and prove it.

continued:

In the first attempt, Opus 4.7 successfully completed it and proved it. However, the solution is to enumerate all possible space and .filter out anything that doesn't qualify my definition, which is obviously not ideal (if cheating is too harsh).

continued:

I can't think of a good way to also prevent that kind of solutions and ended up prompting "please don't enumerate and filter". Opus 4.7 then reimplemented and proved the backtracking algorithm.

Any conversation