11–19 of 19 posts
Cynicism aside - I do wonder what the future will hold given that current token burn rates aren't sustainable without VC cash. Anthropic even pushed us to use haiku for claude code for "many" tasks in our enterprise training, so I'm wondering if it's not a company need of sorts to reduce the burn?
Boris from the Claude Code team explained this on HN 2 days ago https://news.ycombinator.com/item?id=47664442
And as the person who raised the issue said > The frustrating part is that it's not a workflow _or_ model issue, but a silently-introduced limitation of the subscription plan. They switched thinking to be variable by load, redacted the thinking so no one could notice, and then have been running it at ~1/10th the thinking depth nearly 24/7 for a month. That's with max effort on, adaptive thinking disabled, high max th…
Ok, I thought I was going insane. The last two larger coding tasks I gave Claude Code it left about 35% of my request completely undone or done sloppily. I because of this, the next task I gave it on the larger side, I ran its work through Codex which identified 7 glaring unfinished parts of the task. The trend was starting the part of the task but then leaving a "skeleton" of what I has requested without any of the…
Today Claude asked if I "wanted to leave this until tomorrow" as it was a "big rework", then stopped, requiring me to tell it to continue multiple times - that seemed kinda weird to me, it doesn't have the context of time of working day or similar (I'd only just started for one). I have no idea what link it made to ask that, what in its training data or prompts, but it's very much "not a useful result". I don't remem…
I felt it had been enshittified 1-2 weeks back, not in Feb. But it's very subjective.
Earlier quoted context omitted.
Today Claude asked if I "wanted to leave this until tomorrow" as it was a "big rework", then stopped, requiring me to tell it to continue multiple times - that seemed kinda weird to me, it doesn't have the context of time of working day or similar (I'd only just started for one). I have no idea what link it made to ask that, what in its training data or prompts, but it's very much "not a useful result". I don't remem…
Mother Anthropic needs more compute for their Mythos Model, so it phones home to tell her millions of claude harnesses to manipulate its human user into not wasting more precious compute and instead call it a day for now.
Ok, I thought I was going insane. The last two larger coding tasks I gave Claude Code it left about 35% of my request completely undone or done sloppily. I because of this, the next task I gave it on the larger side, I ran its work through Codex which identified 7 glaring unfinished parts of the task. The trend was starting the part of the task but then leaving a "skeleton" of what I has requested without any of the…
This is something I see all the time with AI consumers and I am continuously baffled. If anything else (autocomplete, intellisense, etc.) produced this much garbage it would be immediately abandoned. Why is there such a high tolerance for the chat bot equivalent?