Most of us know what is it about. The problem is Sony and other companies have plenty of money for lobbying governments. What options do we have? I know it’s mostly technical forum but is there any lawyer or government representative who can help?
It's hard to believe Composer 2.5 is that good. I tried to compare it with GLM 5.2 or Opus 4.6 and it lacked thinking about the problem and critical reasoning. It's great for executing plans made by other models, but even then it does some weird code manipulation that is far from how other files around actually work.
I'm not using Cursor at the moment, but when I did (not too long ago) my experience was similar. Plan with Opus, implement with Composer, clean up with Opus.
Composer did a competent but not amazing job with a good plan. What I really liked though is it was fast! Opus could take 30 minutes to do something Composer would get done in 5-10 minutes. Of course the output wasn't perfect, but that's why I'd do a cleanup pass using Opus or Codex.
It's all a balance though, constantly changing and completely dependent on the problem you're solving. I just remain flexible and adapt my process to what's working best in the moment.
Interesting. If I may: What was this "clean up" pass? A code review? A code review with specialized prompt? A focused review to check for edge cases / logic errors / api misuse? Or, something else specific to the codebase?
Have you settled on what the clean up pass should look like? Or, do you keep experimenting with it?
In case one might not have been aware: Composer 2 was Kimi Base 2.5 post-trained (RL'd) by Cursor: https://news.ycombinator.com/item?id=48507474. Composer 2.5 might be something totally different.
I end every project with a long interrogation session. Why did you do this? Is there a better approach you didn't consider? Do the naming conventions follow the project idioms? Justify the decision you made here, providing evidence. I disagree with your approach, etc. etc.
Doesn't matter which model wrote the code, they all make mistakes. This is the same stuff I'd do with any junior engineer's PR and it leads to better quality outcomes (something I care about and am finding hard to let go).
Fable is particularly good at having this back and forth I'm discovering.
I read these and think it is just the jagged edge. I do not doubt your personal experience, I have used Composer 2.5 (via Grok and the credits I get with my X premium account) the past month.
I am not building rockets, but have been quite impressed. All the models do dumb things sometimes, it has done the work I have asked it to pretty well though and has done to me some impressive work.
It is fast on Grok, for other models I have worked extensively with I think it is better than gemini 3.1 (3.5 and antigravity for me is worse than the prior gemini cli). And is comparable to Opus 4.6. (Have not used the more recent models in Claude Code.)
> More and more I find myself trying to stop Opus from doing something stupid, and at every turn I need to tell it to stop overcomplicating things
Yeah, that’s my thoughts as well. I feel it’s great for benchmarks and some tasks while in other it tries to spend as much tokens as possible, tries to overcomplicate task and needs seconds or third round of steering that costs. With the scale Anthropic operates I bet it’s huge amount of extra money just to make sure their model works.
Over the last few years, I’ve felt as though I’ve been living in a feverish dream all the time. Laws, regulations and general changes in the world are so detached from reality and so far removed from the reality they are meant to serve. And this is yet another example.
It's six years later, and what happened during a public health emergency is still the most significant impingement upon personal liberty occupying your headspace? If you earnestly care about liberty, get off your simulated hobby horse and come back to reality. It's exactly this kind of disconnected nonsense that has encouraged the authoritarians to run wild.
Is he wrong though? Lots of bad precedents were set during that emergency, the consequences of which were still living with.
The Overton window moved in a deeply authoritarian direction during that time period. Politicians across the spectrum have internalized that move and are restricting freedom in far more overt ways than were possible prior to that emergency.
If you want to prevent future abuses, understanding how and why past abuses happened seems quite reasonable. I don’t find such an idea nonsense or disconnected from reality at all.
I don't see "lots of bad precedents", so please elaborate on what you mean.
What I saw were a bunch of temporary measures directly supporting public health, in line with past precedents from prior generations, that were eventually ended - which is a lot better than we can say for any teeth in the ratchet of techno-authoritarianism that has been slowly advancing over the past several decades!
The main thing I saw, and it was more of a demonstration rather than a precedent, was how readily people are led to political rallying cries that go against their own stated values, common sense, and the realities of a situation. How quick people are to tear down our institutions given the right leader that plays to their immediate feelings.
To me, that is the authoritarianism we can draw a direct line from to what we are facing today - basically the continued escalation of giant douche vs turd sandwich. But that's not what people seem to mean when they hand wave about authoritarianism during Covid. Rather such gripes are more often an embrace of that trend!
I think they kind of had to since they allowed OpenAI to do a 5.6 "preview to trusted parties" today. The other driver is that the DoD/NSA wanted to get access to Mythos again. I figure OAI will now do several weeks of 'preview' like Anthropic did with Mythos. When OAI wants to release 5.6 wider to actually start making money with it, I expect Fable will get approved the same day.
Back when the administration hit Mythos/Fable with the surprise ban, I figured this would be the endgame. They'd keep Anthropic tied up until a competitor had a roughly comparable model ready, then gate them the same.
reply