tba
Joined September 2021
Tell me more about how the Rams are just one Myles Garrett away from being contenders
3
823
pretty underwhelmed so far dot dot dot
6
15
1,425
location tba retweeted
he’s wired in
🤖 Made with AI
362
721
191
17,427
2,193,011
Ask muse to spam them back instead
I've been on the federal Do Not Call registry from day 1, and I'm inundated with unsolicited texts and calls daily, many from local businesses. I want to create an AI agent to aggressively escalate legal action against these companies. You're supposed to be able to get up to $1,500 per violation. Few people try because it's a really time-consuming hassle. But maybe AI agents can automate the process, make me money, and, if successful and widely adopted, raise the cost of these robo calls and texts so much that they are totally eliminated. Is this possible?
1
1
5
1,086
I don't understand why claude's remote control is still so unintuitive. it's literally easier to use Codex's remote control and computer use to send a message to a claude session
1
6
1,017
openai really gave everyone early access to astra and asked them to make video games?
3
10
3,666
Am I the only one who doesn't actually see any new resets when I get this message?
10
1,172
my codex session lost the plot over night and ran through entire week's usage @thsottiaux giv reset pls
1
12
1,228
asked Fable to audit my claude/codex session histories and PRs and got this. shits more real than therapy
I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up. Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption claude.ai/code/artifact/bfdf…
1
7
1,180
I've been using 5.6 for a while now, and yea I mean if you want to solve cancer you should def use Fable. But if you just wanna move some pixels on the screen 5.6 is where it's at
2
8
873
Aren't these benchmarks validation that the simple Fable orchestrator setups that everyone glazes is not actually that great? Writing a plan has always felt like one small part of the equation when it comes to maximizing the output of these models. Most of the complexity comes from iterating when running into the unknowns. From the benchmarks listed these orchestrator setups seem equivalent to Opus. What am I missing?
A few patterns we frequently use with Fable 5: Use Fable 5 as an "advisor." An executor (Sonnet 5) calls Fable 5 for guidance. Most tokens are billed at the lower executor rate.
2
6
960
back to calling it soccer
1
6
705
location tba retweeted
The anime.​com iPhone app is here!🤳 Track what you're watching, rate every show, and stay in your community, all in your pocket and free on the App Store. apps.apple.com/us/app/anime-…
33
39
7
131
14,285
every day waking up without Fable
3
9
354
gpt 5.5 watching me crawl back after Fable shut down
4
1
1
12
991
hope i make it in time
8
324
As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models. Here’s what this means for you: Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error. On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models. We know this is a disruption to your workflows; we appreciate your patience and support.
1
2
557