CS/Math grad turning AI chaos into tools for all. Dad x2, wife-powered. Crafting JoePro.ai. I teach AI to humans, not the other way.
Joined March 2024
- Tweets 4,393
- Following 898
- Followers 822
- Likes 7,015
956 Photos and videos
Before Fable 5 was taken down I built an app.
It is based of MECHA, an orchestration that will produce a structure swarm of agents.
The agents consist of Codex, Claude Code, Hermes, Openclaw, xAI agent endpoint. It can produce 100 agents on a single task.
The app:
thewringer.ai
Because this is produced by Fable 5. Some may say its the most dangerous app in the world.
It is if you want definitive proof of something.
Run it through the wringer.
x.com/JoePro/status/20661291…
3
3
251
JoePro retweeted
Jun 14
Imagine watching your favorite anime scene come alive right in front of you..
878
1,810
8,898
961,026
JoePro retweeted
Jun 13
Wait the jailbreak technique is…asking the model to review a codebase???
65
10
269
29,881
Before Fable 5 was taken down I built an app.
It is based of MECHA, an orchestration that will produce a structure swarm of agents.
The agents consist of Codex, Claude Code, Hermes, Openclaw, xAI agent endpoint. It can produce 100 agents on a single task.
The app:
thewringer.ai
Because this is produced by Fable 5. Some may say its the most dangerous app in the world.
It is if you want definitive proof of something.
Run it through the wringer.
x.com/JoePro/status/20661291…
3
3
251
JoePro retweeted
Jun 12
Meet Kimi-K2.7-Code 👀
Here’s what developers should know to fully unlock K2.7-Code potential：
Jun 12
🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!
🔷 Improved coding & agent performance over K2.6: 21.8% on Kimi Code Bench v2, 11.0% on Program Bench, and 31.5% on MLS Bench Lite.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.
⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.
🔗 Kimi Code: kimi.com/code
🔗 API: platform.moonshot.ai
77
174
2,955
217,981
Talk about a Fable.
Devin is truly incredible. It elevates whatever model being used. I never was impressed by Fable 5. I must not be using the right loop.
Wild news.
Jun 13
We’re removing access to Claude Fable 5 in Cognition products following Anthropic’s latest announcement and the US government directive to suspend access.
All other models remain available in Devin, including Claude Opus 4.8 and GPT-5.5.
Devin Ultra mode will continue to use the most powerful available models.
3
95
Rich Silvers account is a super valuable follow.
He is a man of great ideas and passion in what he does.
Happy Birthday Rich!
1
5
188
Instead of calling it all hype I read more about agentic loops. There is plenty I don't know about structured loops.
I ran it through the Top AI models to see what their best loop looked like.
They came through.
x.com/JoePro/status/20651174…
54
Fable 5 Showdown! Devin vs Claude Code vs OpenClaw vs Hermes. All Running Fable 5 x.com/i/broadcasts/1pJkOOoqw…
103
Lets Go!
I will live stream tonight at 9:30p est.
Test Fable 5!
Devin is the most capable AI Engineer ready to build with the worlds most capable AI model.
If you want something built let me know in the comments.
Jun 9
Claude Fable 5 is now available in Devin.
Fable 5 earns the #1 spot on FrontierCode, our benchmark for real-world engineering tasks that grades mergeability and quality:
1
1
3
1,601
If Andrej Karpathy had some guidence in Fable I'm sure it will be nothing short of a Mythos.
I hope they can handle the devs that are coming!
What are you building?
Jun 9
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.
I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!
2
1
122