founding product engineer @ finto (yc s25) | I got an unhealthy and deep obsession over how products feel
Munich, Germany
Joined September 2025
- Tweets1.5K
- Following304
- Followers100
- Likes724
Giving @bot access to my @t3dotcodes MCP was another great unlock
Can easily let him orchestrate and read my threads, while not relying on cursor cloud agents for actual coding
Asked @t3dotcodes to generate a visual explaining what happens to your body when fasting. Insane results, all in the chat! Dynamic timeline, organ impact etc
Absolute bonkers!!
Lets just say the orchestrator v2 update in @t3dotcodes was quite good
The "working section" is soooo good in @t3dotcodes
Now I can just clean out my sidebar
GREAT @jullerino
more excited for orchestrator v2 than for a new model drop at this point
@jullerino WHENNNN
First feedback on SWE-2 by @cognition
- Its very good for working on clear defined tasks, like tickets or specs written by other models
- It was a bit on the slower side but I think that was mostly because of high strain on their systems (Its free on devin currently)
- Great quality output, it replaced grok as my executor agent
- Devin Fusion (fable5.1+swe-2) Is very very good!
- Burned about 20% of my weekly quota in a day ($200 plan)
Will continue using and exploring it 🫡
T3 Code and T3 Connect are so good and easy to setup, converted my unused gaming pc to a Linux Server which acts as my workhorse now, where all the agents run, its always online and super fast. Using my mac/iphone solely for orchestration and its soooooo good!
I will be trying out @devindesktop heavily in the next weeks, especially Fusion, Cloud Agents & Computer Use. Excited!
We independently benchmarked Devin Fusion for its release today - this is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index, and it effectively retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs
Devin Fusion runs a frontier lead model with a cost-efficient sidekick. We tested configurations from Cognition combining frontier models from Anthropic and OpenAI with their new SWE-2 (medium) as a sidekick model. Configured with Claude Fable 5.1 (xhigh) + SWE-2 (medium), Devin Fusion scores 62 on the Coding Agent Index v1.5, while with GPT-6 Astra (xhigh) + SWE-2 (medium) it scores 59. The Fable configuration has the higher score, while the Astra configuration is 43% less expensive and completes tasks 31% faster.
Congratulations to @cognition on the release! See below for our results and analysis 🧵
been building something called Good Catch :)
synthetic customers try your product, share what they’re thinking and where they get stuck. your coding agents can get the review via MCP, it can also run in your CI. Like coderabbit but for UX.
basically trying to catch the stuff you’d otherwise hear about from customers after shipping. UX & "taste" stuff.
opening up invite-only testing. if you’re building a web product with AI, would love for you to try it. dm me
reminder that every L you take can be a W in disguise if you dont give up
if @supastarter sales never tanked, @jonathan_wilke would not have made outbid.lol
Well deserved!
