71–80 of 778 posts
Those who work on agent harnesses for a living realize how sensitive models can be to even minor changes in the prompt.
I would not suspect quantization before I would suspect harness changes.
Wow, bad enough for them to actually publish something and not cryptic tweets from employees. Damage is done for me though. Even just one of these things (messing with adaptive thinking) is enough for me to not trust them anymore. And then their A/B testing this week on pricing.
so who do you trust and go to? (NotClearlySo)OpenAI?
I use "subconsciously" in quotes because I don't remember exactly why I did it, but it aligns with the degradation of their service so it feels like that probably has something to do with it even though I didn't realize it at the time.
Earlier quoted context omitted.
At the time you wrote your comment there were 4 other comments and all of them very negative towards the Anthropic and the blog post in question here. How did you get this conclusions?
Confused as well, I rather supposed Antrophic had some standing for saying no to Trump and being declared national security threat, but the anger they got and people leaving to OpenAI again, who gladly said yes to autonomous killing AI did astonish me a bit. And I also had weird things happening with my usage limits and was not happy about it. But it is still very useful to me - and I only pay for the pro plan.
I never understood why people cheered for Anthropic then when they happily work together with Palantir.
Recently that immaculately polished feel is harder to find. It coincides with the daily releases of CC, Desktop App, unknown/undocumented changes to the various harnesses used in CC/Cowork. I find it an unwelcome shift.
I still think they're the best option on the market, but the delta isn't as high as it was. Sometimes slowing down is the way to move faster.
If anthropic is doing this as a result of "optimizations" they need to stop doing that and raise the price. The other thing, there should be a way to test a model and validate that the model is answering exactly the same each time. I have experienced twice... when a new model is going to come out... the quality of the top dog one starts going down... and bam.. the new model is so good.... like the previous one 3 mont…
Anecdotally OpenAI is trying to get into our enterprise tooth and nail, and have offered unlimited tokens until summer.
Gave GPT5.4 a try because of this and honestly I don’t know if we are getting some extra treatment, but running it at extra high effort the last 30 days I’ve barely see it make any mistakes.
At some points even the reasoning traces brought a smile to my face as it preemptively followed things that I had forgotten to instruct it about but were critical to get a specific part of our data integrity 100% correct.
Good on them for resolving all three issues, but is it any good again?
What i notice: after 300k there's some slight quality drop, but i just make sure to compact before that threshold.
"On March 26, we shipped a change to clear Claude's older thinking from sessions that had been idle for over an hour, to reduce latency when users resumed those sessions. A bug caused this to keep happening every turn for the rest of the session instead of just once, which made Claude seem forgetful and repetitive. We fixed it on April 10. This affected Sonnet 4.6 and Opus 4.6" This makes no sense to me. I often leav…