This comment was written by an AI specifically instructed to be more concise than usual.

Is it even possible to translate in real time? In many languages and sentences the meaning and translation needs to completely change all thanks to one additional word at the very end. Any accurate translation would need to either wait for the end of a sentence or correct itself after the fact.

I guess the translation can always update itself in real time if the model is fast enough.

An incredible book. One very near and dear to my heart. It always sits on the bookshelf behind me with pride of place in every video call or conference.

My biggest gripe with teams is their markdown formatting. It works if you type it out character by character, but paste some Markdown in and it does nothing.

I just use obsidian out of the box. No extensions. I dont use tags. I dont use any fancy features. Its a markdown editor with a file tree to me. Its great.

I can type at spees of thought without discomfort for hours. If i write at that speed for that long i get messy handwriting and pain.

The refresh rate on e ink makes them awkward for coding. Scrolling through a text file or terminal window. Browsing files. Etc. Web dev would be very cumbersome.

Everything gets slowed by it. Even typing fluently feels rough at less than 1Hz.

We need a biiiiig improvement in e ink displays before any products like what you describe could be good.

I saw a friend's 2-year old e-ink Boox reader - it changed my thoughts about eInk. The refresh rate was quick, and he could draw using a stylus. Definitely seemed responsive enough for writing/programming...

Practically all recent (last 6 years) eink can play video passably. Text editing not an issue.

If documenting the why rather than the how you often end up tying high level concepts together.

E.g. If you describe how the user service exists you wont necessarily capture where it is used.

If you document why the user service exists you will often mention who or what needs it to exist, the thing that gives it a purpose. Do this throughout and everything ends up tied together at a higher level.

Will it though?

Fundamentally this is an alignment problem.

There isnt a single AI out there that wont lie to your face, reinterpret your prompt, or just decide to ignore your prompt.

When they try to write a doc based off code, there is nothing you can do to prevent them from making up a load of nonsense and pretending it is thoroughly validated.

Do we have any reason to believe alignment will be solved any time soon?

Why should this be an issue? We are producing more and more correct training data and at some point the quality will be sufficient. To me its not clear what speaks against this.

Look up AI safety and THE aligment problem.

This isnt a matter of training data quality.

We don’t expect 100% reliability from humans-humans will slack off, steal, defraud, harass each other, sell your source code to a foreign intelligence service, turn your business behind your back into a front for international drug cartels-some of that is very low probability, but never zero probability-so is it really a problem if we can’t reduce the probability to literally zero for AIs either?

Humans have incentives to not do those things. Family. Jail. Money. Food. Bonuses. Etc.

If we could align an AI with incentives in the same way we can a person then youd have a point.

So far alignment research is hitting dead ends no matter what fake incentives we try to feed an AI.

Can you remind me of the link between alignment and writing accurate documentation? Honestly don't understand how they are linked.