[dead]
Parent comment has the rhythm of an AI comment. Caught myself not realizing it until you mentioned it. Seems like I am more in tune with LLM slop on twitter, which is usually much worse. But on second sight it's clear…
do you use it with git worktrees? or how do you handle multiple claudes?
Not working on it (yet), but I wish the jj <-> github story was a little more ergonomic. Additionally, I am really missing support for stacked diffs, ie, easily pushing a number of commits into one PR on github each…
I'll have a look into what the transfer story from mattermost->element looks like.
Thank you for pointing to these details!
This stance strikes me as questionable, to use the first hunch that comes to mind to seed doubt in a topic that is researched and reported by multiple fairly reputable sources and multiple people on the ground.
I'm gonna go out on a limb and say that this is LLM written slop that is badly edited by a human. Factually correct but the awful writing remains.
how so? sound like you are running Kimi K2 / GLM? What agents do you give it and how do you handle web search and computer use well?
Thank you xethos, this has been exactly the kind of opinion and experience report that I've been looking for. the one thing I really want beyond persistent over whatsapp is threads. I hope matrix has a similarly trivial…
Skimmed through it; mostly reading the paragraphs above each picture. The irony of which is not lost on me :) Really enjoyed the part talking about Tolkien. It reminds me of my own LOTR experience: I finished the…
I recently switched a bunch of friends from a project-oriented whatsapp chat to self-hosted mattermost, because I wanted permanent storage for messages and attachments, and threads, and did not want to pay slack in…
Merry Christmas! This is why I like hackernews.
almost seems like there is now too much money in software. the old times felt like computer science was mostly a science.
can someone clarify the situation that self-hosted free (as in beer) community mattermosts are/will be in?
I think features of the language can make it much easier (read: possible) for the compiler to recognize when a function is tail call optimizable. Not every recursion will be, so it matters greatly what the actual…
ok but Germans also use not bad as their highest praise and are from the west etc.
The people I know who „think in math“ don’t think in the syntax of the written notation, including myself.
I thought (and think) that the teaclipper‘s square sail rigs wouldn’t be considered state of the art for any course the ship might sail.
Transformers try to give you capabilities by doing two things interleaved (in layers) multiple times: - apply learned knowledge from its parameters to every part of the input representation („tokenized“, ie, chunkified…
50C is terribly hot for a swim. Hot spring baths usually top out around 42-43C
This is a great resource for datasets for medical imaging with AI and surprisingly complete in the areas that I searched.
fair point, I appreciate AI researcher intuition about AI much more than CEO hunch boldly stated but not even firm on the terminology.
With all due respect, what does it say about us that „famous researcher voices his speculative opinion“ is an instant top 1 on hackernews?
[dead]
Parent comment has the rhythm of an AI comment. Caught myself not realizing it until you mentioned it. Seems like I am more in tune with LLM slop on twitter, which is usually much worse. But on second sight it's clear…
do you use it with git worktrees? or how do you handle multiple claudes?
Not working on it (yet), but I wish the jj <-> github story was a little more ergonomic. Additionally, I am really missing support for stacked diffs, ie, easily pushing a number of commits into one PR on github each…
I'll have a look into what the transfer story from mattermost->element looks like.
Thank you for pointing to these details!
This stance strikes me as questionable, to use the first hunch that comes to mind to seed doubt in a topic that is researched and reported by multiple fairly reputable sources and multiple people on the ground.
I'm gonna go out on a limb and say that this is LLM written slop that is badly edited by a human. Factually correct but the awful writing remains.
how so? sound like you are running Kimi K2 / GLM? What agents do you give it and how do you handle web search and computer use well?
Thank you xethos, this has been exactly the kind of opinion and experience report that I've been looking for. the one thing I really want beyond persistent over whatsapp is threads. I hope matrix has a similarly trivial…
Skimmed through it; mostly reading the paragraphs above each picture. The irony of which is not lost on me :) Really enjoyed the part talking about Tolkien. It reminds me of my own LOTR experience: I finished the…
I recently switched a bunch of friends from a project-oriented whatsapp chat to self-hosted mattermost, because I wanted permanent storage for messages and attachments, and threads, and did not want to pay slack in…
I recently switched a bunch of friends from a project-oriented whatsapp chat to self-hosted mattermost, because I wanted permanent storage for messages and attachments, and threads, and did not want to pay slack in…
Merry Christmas! This is why I like hackernews.
almost seems like there is now too much money in software. the old times felt like computer science was mostly a science.
can someone clarify the situation that self-hosted free (as in beer) community mattermosts are/will be in?
I think features of the language can make it much easier (read: possible) for the compiler to recognize when a function is tail call optimizable. Not every recursion will be, so it matters greatly what the actual…
ok but Germans also use not bad as their highest praise and are from the west etc.
The people I know who „think in math“ don’t think in the syntax of the written notation, including myself.
I thought (and think) that the teaclipper‘s square sail rigs wouldn’t be considered state of the art for any course the ship might sail.
Transformers try to give you capabilities by doing two things interleaved (in layers) multiple times: - apply learned knowledge from its parameters to every part of the input representation („tokenized“, ie, chunkified…
50C is terribly hot for a swim. Hot spring baths usually top out around 42-43C
This is a great resource for datasets for medical imaging with AI and surprisingly complete in the areas that I searched.
fair point, I appreciate AI researcher intuition about AI much more than CEO hunch boldly stated but not even firm on the terminology.
With all due respect, what does it say about us that „famous researcher voices his speculative opinion“ is an instant top 1 on hackernews?