Joined February 2015
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Replying to @DavidOndrej1
I have yet to see a reasonable argument on what opus 5.5 is lacking. It’s such a good model.
22
Replying to @elonmusk
Ara is soo good...
28
Replying to @poteto @bot
@bot learn from this post and give me your feedback on how it can improve my agents.
1
23
Replying to @poteto
“note: this won't mean the code will be Good, but it should at least work” @poteto can you elaborate?
577
Replying to @thsottiaux
? 2x week usage so we go back to what we had last week before @OpenAI cut our usage by half? Ya this is the reason I’ll be switching
28
Replying to @Michael_Fenech_
@bot take this prompt and do a test run of instructions
1
1
151
CelestialSyntax retweeted
ClaudeDevs
@ClaudeDevsOct 9
Claude Managed Agents dynamic workflows are now available in public beta. It's a new type of multiagent orchestration, built for your most ambitious workloads. A lead agent writes a plan that runs across many agents in phases, combining the results at the end.
429
729
286
12,562
1,031,273
Replying to @poteto @bot
@bot do this for me too.
3
Replying to @iruletheworldmo
Next phase should be to fix their limits on the $100 plan and I’m all in.
2
268
Replying to @Av1dlive
Can anyone tell me if the supergrok plus $100/month plan has decent weekly usage? Would I still have to worry about limits if I use it often throughout the day but not like 24/7?
2
417
Claude
@claudeaiOct 7
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.
9
Replying to @thsottiaux
Bring back our $200 plan pre-50% cut so I can gain confidence in OpenAI again…
1,240
Replying to @thsottiaux
Our $200 plan we had two weeks ago
4
Replying to @thsottiaux
Too inconsistent to build on it. Not sure when usage will be cut in half one week or move to a $500 plan the next. Last thing I want is to have all my work in something and rugs are pulled.
37
@lydiahallie I appreciate the credit but it functionally has no use other than what seems to be a way to condition customers to “cloud” sessions of all kinds being separate billing outside of subs.
1
415
Replying to @DavidRBellamy
I appreciate your post but this is another “AI can’t replicate real human work” argument that boomer devs make. It’s not about what AI can do now or in the next year. The capabilities of these models coupled with human ingenuity there’s nothing that can’t be done.
3
191
Replying to @theo
worry. Working on an app that is everything STT, including meeting notes, ai chat with your memos and meetings, slack integration, sharing, choosing your transcription model and inference model, etc
110
Replying to @danshipper
No community note needed here. The truth is probly even more shocking.
286