211–220 of 363 posts
They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.
[flagged]
They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.
> "The model is getting worse" has been rumored so often, by now, shouldn't there be some trusted group(s) continually testing the models so we have evidence beyond anecdote? https://news.ycombinator.com/item?id=45097263#45098202
> Investigating - Last week, we opened an incident to investigate degraded quality in some Claude model responses. We found two separate issues that we’ve now resolved. We are continuing to monitor for any ongoing quality issues, including reports of degradation for Claude Opus 4.1.
Earlier quoted context omitted.
I don’t think you’re crazy, something is off in their models. As an example I’ve been using an MCP tool to provide table schemas to Claude for months. There was a point where it stopped recognizing the tool unless mentioned in early August. Maybe that’s related to their degraded quality issue. This morning after pulling the correct schema info Sonnet started hallucinating columns (from Shopify’s API docs) and added t…
ive been thinking its that my company mcp has blown up in context size, but using claude without claude code, i get context window overflows constantly now. another option could be a system prompt change to make it too long?
As a baseline from a real conversation, 270 lines of sql is ~2500 tokens. Every language will be different, this is what I have open.
When Claude edits an artifact it seems to keep the revisions in the chat context, plus it’s doing multiple changes per revision.
After 10 iterations on a 1k loc artifact (10k tokens) you’re at 100k tokens.
claude.ai has a 200k token window according to their docs (not sure if that’s accurate though).
Depending on how Claude is doing those in place edits that could be the whole budget right there.
Earlier quoted context omitted.
In agent mode there is a whitelist of commands in the VScode settings that it can do without confirmation. When I went to edit that file, copilot suggested adding "rm -rf *".
This must be a mistake. It should be "rm -rf /*"
They need to focus on fixing reliability first. Their systems constantly go down and it appears they are having to quantise the models to keep up with demand, reducing intelligence significantly. New features like this feel pointless when the underlying model is becoming unusable.
Earlier quoted context omitted.
I'd like to give these a try - what's your way of using them? I mostly use Claude because of Claude Code. Not sure what agentic coding tools people are using these days with OSS models. I'm not a big fan of manually uploading files into a web UI.
The most private way is to use them on your own machine; a Mac Studio maxed out to 512GB RAM can run GLM-4.5 at FP8 with fairly long context, for example. If you don't have the hardware to run it locally, let me shill my own company for a minute: Synthetic [1] has a $20/month subscription to most of the good open-weight coding LLMs, with higher rate limits than Claude's $20/month sub. And our $60/month sub has higher…
If you can find a way to secure the requests even during the 14 day period, or anonymize them while allowing the developers to do their job, you can have my money today. I think privacy/data security is the #1 concern for me, especially if the agents will be supporting me in all kinds of personal tasks.
Earlier quoted context omitted.
Can you still code without it?
I'm not sure how saying it won't even run CLI commands has anything to do with my ability to code with or without it.
Earlier quoted context omitted.
I don’t think you’re crazy, something is off in their models. As an example I’ve been using an MCP tool to provide table schemas to Claude for months. There was a point where it stopped recognizing the tool unless mentioned in early August. Maybe that’s related to their degraded quality issue. This morning after pulling the correct schema info Sonnet started hallucinating columns (from Shopify’s API docs) and added t…
I have read so many anecdotes about so many models that "were great" and aren't now. I actually think this is psychological bias. It got a few things right early on, and that's what you remember. As time passes, the errors add up, until the memory doesn't match reality. The "new shiny" feeling goes away, and you perceive it for what it really is: a kind of shitty slot machine > personally am frustrated that there’s n…