Beinas
23 posts
@rezoundous If instead they could fix whatever they did to mess up so much token consumption I bet it would be way more impactful in any reputation and market share getting lost
English
@rezoundous For $25/$125 pricing? Nah I don’t think anyone would really care about it… even for enterprise that is a hell of a lot money
English
this is how GPT-5.5 holds up against Claude Mythos in benchmarks
English
@ViniciusBueno86 @ClaudeDevs I will likely subscribe this weekend and have a go with it on non critical stuff to get the feeling, are you on the $100 or $200 one?
I agree, as is, CC is no longer reliable
English
@Beinasest @ClaudeDevs Cancelei minha assinatura, ficou inviável usar, estou usando o Pro do Codex, mesmas tarefas, mesmo uso, não consigo gastar mais e 20% entre as janelas de 5h. O custo benefício é monstruoso.
Português
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found.
All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.
English
Realizing that soon Claude will connect to your bank accounts and pay bills automatically.
Claude@claudeai
Claude can now connect to more of the apps you use outside of work, including @Tripadvisor, @bookingcom, @resy, @Instacart, @Spotify, @audible_com, @AllTrails, @thumbtack, Intuit @turbotax, and more.
English
Available now on web, desktop, and mobile (beta) across all plans.
Read more: claude.com/blog/connector…
English
Claude can now connect to more of the apps you use outside of work, including @Tripadvisor, @bookingcom, @resy, @Instacart, @Spotify, @audible_com, @AllTrails, @thumbtack, Intuit @turbotax, and more.
English
@Beinasest @ClaudeDevs workflows that would take 1-1.5% of the 5h limit last month now take up about 6%
English
I am a 20x myself and this was yesterday right after the reset. I think there is being very rare occasions I got so high on the 5hrs, but, worse than the 5hrs was the weekly limit… 7% for a 64% 5hrs?
And please.. don’t say it’s “context window” or plugins or whatever else, my environment is exactly the same and I have been handling the workflow pretty much in the same way for ages, I can clearly say the consumption is really off
English
It’s not a matter of “run this or that to see what is burning your tokens”, the point is: precisely the same work we would perform before and see 1 or 2% of 5hrs capacity, now became 8, 9%. Same plugins, same code base, every now and then running compact (which I used to do anyway).
So please, the narrative of “see what’s burning your tokens” is pretty much irrelevant on what the actual issue really is… but you know that I am sure
English
@PawelHuryn I agree that this week was better indeed… but after the reset things went mad, my limit is just burning down as crazy since after that (was alright before, same workflow)
English
Respect for Anthropic's Claude Code post-mortem.
The caching bug cleared thinking every turn. Every token after it shifted forcing a full cache rewrite every turn.
Same workload, week before the fix: Max 20x plan burned in 3-5 days.
This week, post-fix: 36% of the plan was enough. I never thought I could downgrade.
ClaudeDevs@ClaudeDevs
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.
Raszyn, Polska 🇵🇱 English
@dedene @AnthropicAI Yes, and in under 3 hours since I already burned through 4% of the new weekly limit on the 20x plan doing some very light weight stuff…
English
@heygeorgekal But did you actually got the plan implemented or just created?
English
Didn't expect any different but one juicy feature (1 plan and 2 iteration prompts) for my game engine and almost 50% of the 5x plan used.
I guess it's time to fully switch to Codex next month.
English
@robinebers In practice that’s not correct, even though the price per token is the same, it consumes more tokens
English
Opus 4.7 is a significantly better model at the exact same price
this is good ngl
English
@dramaricic Careful there, just by thinking on 4.7 you might burn your weekly limit already
English
I know why Claude Opus 4.6 got dumber.
Its because Opus 4.7 is going live next week.
I’m I wrong?
English
@kimmonismus Careful there, just by thinking about Opus 4.7 you might exceed your usage limit
English
Claude Opus 4.7 probably this week + design tool, via TheInformation!
Anthropic will launch Claude Opus 4.7 and a new prompt-based design tool for websites and presentations this week, while its more advanced model Claude Mythos is already being tested for cybersecurity use cases.
English
Now in research preview: routines in Claude Code.
Configure a routine once (a prompt, a repo, and your connectors), and it can run on a schedule, from an API call, or in response to an event.
Routines run on our web infrastructure, so you don't have to keep your laptop open.
English
Need my whole 100% of weekly Max 20x available to use it for a bit probably? (And probably starting a couple fresh sessions in the middle to keep context under control)…
Why building more and more stuff if not even what is in place is stable?… sincerely, you guys already had an AMAZING product 3 weeks ago, then it all went downhill unfortunately, it’s like self sabotage
English
there's a turbotax connector in Claude Code now, so glad I procrastinated on taxes 😭
Henry Shi@henrythe9ths
Tax season is here and a connector is all it takes to make @claudeai way more useful. Checkout what we just shipped: Connect TurboTax or Aiwyn Tax (formerly Column Tax) to Claude to estimate your refund, see what you may owe, and get a better understanding on the forms before you file.
English