Pinned Tweet
A playbook for building apps:
- find a problem you have
- open a LLM provider (like ChatGPT, Claude, Gemini, Grok, etc)
- chat about your problem and get help from there
- iterate
- at some point, it will become harder for the LLM to manage the context and the memory
- then it's time to ask the LLM to give you a prompt that will give you all the info from that chat to help you turn that chat into an app (like an iOS app, MacOS app, etc)
- iterate until you have a stable version
- go distribute it as there will be more people to have that problem as well
Right now I'm doing this. Making an iOS app using Devin for my GYM sessions. Now it is tailored to my needs, but I'm pretty sure it can be used by others that need my structure.
Florin retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/DeepI…
1/4
Florin retweeted
Devin Fusion. Better and cheaper.
Devin Fusion has claimed a top score of 68 on the @ArtificialAnlys Coding Agent Index with an Opus 5.5 lead and GPT-6 Luna sidekick.
Devin Fusion outperforms Claude Code with Opus 5.5 on both performance and price – earning a score of 68 at a 31% lower cost per task.
Florin retweeted
Devin Fusion tied #1 on Artificial Analysis Coding Agent Index
Outperforms Claude Code w/ Opus 5.5 on both performance and price, at 31% lower cost per task
Fusion has a wide array of model combinations, so as more models become available the design space for finding optimal / specialized combinations grows.
Devin Fusion has claimed a top score of 68 on the @ArtificialAnlys Coding Agent Index with an Opus 5.5 lead and GPT-6 Luna sidekick.
Devin Fusion outperforms Claude Code with Opus 5.5 on both performance and price – earning a score of 68 at a 31% lower cost per task.
Florin retweeted
Scraped Greenhouse, Lever and Ashby for 821 open FDE jobs at 292 companies, including 336 remote
forwarddeployed.fun
PagerDuty just pinged me. Investigating now, go back to bed.
Florin retweeted
I love automations that enable us to stop operating software and return to innovating and building it.
Devin Oncall is the best harness at diagnosing and fixing production failures, and does so autonomously so engineers can just "build".
Florin retweeted
Devin Oncall detects emerging problems before customers notice them, allowing teams to act early and contain incidents before they escalate.
Engineers can focus on building the future, not maintaining the past.
Replying to @DomAtSiteSage
you can definitely mix and match and take what you need! pstack skills all have disable-model-invocation: true so they don’t get auto injected into every session, so there’s no token cost to installing it
try /poteto-help too to see which skills you might want to use
pstack-codex is synced with pstack 0.15.25
what's new:
ketchup. catches you up on a long chat so you don't scroll back through 200 messages
in-your-own-words. codex says the goal back to you before it starts, so you catch a misunderstanding before it turns into wrong code
sharpen. it pushes on the plan before any code gets written
the pr watcher got better too, and it still stops at merge-ready. it never merges unless you ask
if you're on codex, this gets you the same engineering rules poteto wrote for cursor. 53 skills, and the installer backs up your setup first
Florin retweeted
I'm a newcomer to @poteto's plist; But it seems to me that there is some very significant wisdom encoded in there. I suspect you could teach a master class on the principles.
I can invest much more for sure
Nvidia will announce $28 of AI investments in Europe this week $NVDA




















