founding product engineer @ finto (yc s25) | I got an unhealthy and deep obsession over how products feel
Munich, Germany
- Tweets 1,451
- Following 295
- Followers 91
- Likes 674
more excited for orchestrator v2 than for a new model drop at this point
@jullerino WHENNNN
1
175
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 🫡
1
196
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!
51
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 🧵
103
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
2
181
just setup t3 connect on my mac + iphone for the first time, insane smooth and easy wtf
gg @theo
1
1
95
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!
51
Since usage is already tracked in @t3dotcodes, I would really love to see my remaining limits in there aswell, hate having to open the claude app to see them (or start a cli session)
75
I love AI, for my own UGC content I have built a fully automatic and agent friendly insta dm engine
(You give a script and it generates a video of the script as an insta chat, with the same UI, animations, iOS keyboard typing etc)
1
1
59
third day, third tiktok and within 2-3 minutes the algo pushed it to almost 1k views 🤩
still no installs on the app but we keep grinding
1
42
we all know who is NOT gonna adopt that
Introducing Agent Plugins, an open standard for extending agents.
Supports Agent Skills and MCP, with more to come.
Built in collaboration with: @awsdevelopers, @code, @cursor_ai, @github, and @openaidevs.
vercel.com/blog/introducing-…
57
/wait-what makes opus5 output actually readable
Try it out and you will realize Opus5 is not as bad as X makes it seem, but rather just really bad at communicating with humans
mattpocock/skills v1.2 is out!
We're now the 19th most-starred repo of all time. 13.5m downloads on skills.sh. Thanks for your support!
Here's what's new:
- Docs: the community's biggest ask. Every skill documented, with explanations of the main flows + troubleshooting
- Claude Plugin: install via Claude's official marketplace
- Codex Support: full Codex support via agents/openai.yaml files
Updated Skills:
- /grilling now asks you questions in rounds, not one-by-one
- /prototype now uses HTML instead of a TUI for building logic prototypes - easier to share and far richer
- /writing-for-agents renamed from /writing-great-skills, use it for ANYTHING your agents read (AGENTS.md, system prompts, docs)
New Skills:
- /wizard: tired of provisioning infra? Get your agent to build you a TUI to walk you through it
- /to-questionnaire: hit a grilling question you can't answer? Turn the session into a doc you can walk through on a call with a colleague
- /wait-what: no idea what the model said? Refocus it in your domain language and simplify with ASD-STE100
Full changelog + docs below. Video soon!
2
164