651–660 of 1001 posts
Are we unemployed yet?
No? The hardest part of my SWE job is not the actual coding.
https://youtu.be/8brENzmq1pE?t=1544
I feel like everyone is counting chickens before they hatch here with all the doomsday predictions and extrapolating LLM capability into infinity.
People that seem to overhype this seem to either be non-technical or are just making landing pages.
Earlier quoted context omitted.
Thanks for the response, I appreciate it. I do notice variation in quality throughout the day. I use it primarily for searching documentation since it’s faster than google in most case, often it is on point, but also it seems off at times, inaccurate or shallow maybe. In some cases I just end the session.
Usually I find this kind of variation is due to context management. Accuracy can decreases at large context sizes. OpenAI's compaction handles this better than anyone else, but it's still an issue. If you are seeing this kind of thing start a new chat and re-run the same query. You'll usually see an improvement.
Earlier quoted context omitted.
Do you have a specific reference? I'm curious to see hard data and models.... I think this makes sense, but I haven't figured out how to see the numbers or think about it.
I was able to find the podcast. Question is at 33:30. He doesn't give hard data but he explains his reasoning. https://youtu.be/mYDSSRS-B5U
And why is that? Should they not be interested in sharing the numbers to shut up their critics, esp. now that AI detractors seem to be growing mindshare among investors?
Earlier quoted context omitted.
Also explains why Claude Code is a React app outputting to a Terminal. (Seriously.)
I did some debugging on this today. The results are... sobering. Memory comparison of AI coding CLIs (single session, idle): | Tool | Footprint | Peak | Language | |-------------|-----------|--------|---------------| | Codex | 15 MB | 15 MB | Rust | | OpenCode | 130 MB | 130 MB | Go | | Claude Code | 360 MB | 746 MB | Node.js/React | That's a 24x to 50x difference for tools that do the same thing: send text to an API…
Earlier quoted context omitted.
> they still are subsidizing inference costs. They are for sure subsidising costs on all you can prompt packages (20-100-200$ /mo). They do that for data gathering mostly, and at a smaller degree for user retention. > evidence at all that Anthropic or OpenAI is able to make money on inference yet. You can infer that from what 3rd party inference providers are charging. The largest open models atm are dsv3 (~650B para…
most of those subscriptions go unused. I barely use 10% of mine so my unused tokens compensate for the few heavy users
I hope my unused gym subscription pays back the good karma :-)
Earlier quoted context omitted.
To be fair, I don't think "Slugulus Eructo" (the name) is actually in the books. This is what's in my copy: > The smug look on Malfoy’s face flickered. > “No one asked your opinion, you filthy little Mudblood,” he spat. > Harry knew at once that Malfoy had said something really bad because there was an instant uproar at his words. Flint had to dive in front of Malfoy to stop Fred and George jumping on him, Alicia shr…
I have a vague recollection that it might come up named as such in Half-Blood Prince, written in Snape's old potions textbook? In support of that hypothesis, the Fandom site lists it as “mentioned” in Half-Blood Prince, but it says nothing else and I'm traveling and don't have a copy to check, so not sure.
> Ron nodded but did not speak. Harry was reminded forcibly of the time that Ron had accidentally put a slug-vomiting charm on himself. He looked just as pale and sweaty as he had done then, not to mention as reluctant to open his mouth.
There could be something with regional variants but I'm doubtful as the Fandom site uses LEGO Harry Potter: Years 1-4 as the citation of the spell instead of a book.
Maybe the real LLM is the universe and we're figuring this out for someone on Slacker News a level up!
I'm still not sure I understand Anthropic's general strategy right now. They are doing these broad marketing programs trying to take on ChatGPT for "normies". And yet their bread and butter is still clearly coding. Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the depth of research, the type of tasks it can handle, and the qual…
Just tested the new Opus 4.6 (1M context) on a fun needle-in-a-haystack challenge: finding every spell in all Harry Potter books. All 7 books come to ~1.75M tokens, so they don't quite fit yet. (At this rate of progress, mid-April should do it ) For now you can fit the first 4 books (~733K tokens). Results: Opus 4.6 found 49 out of 50 officially documented spells across those 4 books. The only miss was "Slugulus Eruc…
> All 7 books come to ~1.75M tokens How do you know? Each word is one token?
Earlier quoted context omitted.
I looked into it a bit. It stores memories near where it stores JSONL session history. It's per-project (and specific to the machine) Claude pretty aggressively and frequently writes stuff in there. It uses MEMORY.md as sort of the index, and will write out other files with other topics (linking to them from the main MEMORY.md) file. It gives you a convenient way to say "remember this bug for me, we should fix tomorr…
> Persistent directory at ~/.claude/projects/{project-path}/memory/, persists across conversations I create a git worktree, start Claude Code in that tree, and delete after. I notice each worktree gets a memory directory in this location. So is memory fragmented and not combined for the "main" repo?