Building a portfolio of products at https://nitter.gq/t.co/mFAVIoxTzS 🚀
Brasil
Joined April 2009
- Tweets2K
- Following755
- Followers689
- Likes3.1K
Pinned Tweet
how to build anything rn:
- get a hetzner, do, or hostinger vps
- host hermes on it
- add gbrain or implement your own memory vault using qmd + sql
- set up hermes with codex auth -> gpt-5.5 / no reasoning / fast mode
- install orca on your macbook and phone with tailscale to have a nice ide to work on both
- before starting any work, ask hermes to conduct deep research on the subject and save it to gbrain as source material for the project
- use the `/grill-me` skill or a similar prompt to uncover as many unknowns as possible. save results to memory too
- define/write clear evals for every project to determine whether a run was successful
- have hermes iterate over the project until all evals pass, saving all learnings to the vault along the way
- whenever it gets stuck, use memory + a new research or `/grill-me` session to unblock it
rinse and repeat until the work is done. pay attention to the process. develop a feeling for how long tasks should take and do not be afraid to stop a model mid session to ask for status and why it's taking so long.
Crazyyyyyy
i went to bed and asked claude to paint an autumn tree overnight.
at around 4am, it realised that it didn't have some shades -- so it stopped and titrated its own paint: diluting red, sienna and madder step by step on a second palette, then measuring each pocket from a photo.
woke up to this beautiful watercolor painting. 303 brush marks, took about 4.5 hours 🍂 (still working on the speed)
All very true
I think we're going to see a new wave of interest in usability.
Chat is hard on the brain. Total opposite of what Don Norman wrote about. 100% holding in your head, remembering things, special modes, etc.
Nobody wants the stuff in their kitchen to be in a different place each time they walk in.
System of record + recognizable display are not going away. What's new is how fluidly we can change state WITHIN those as users.
Jonata Santos retweeted
Formal verification is the only way, fully convinced.
Shoutout to Taelin for seeing it before most of us and building it out.
Someone needs to do a YouTube series “formal verification for agent acceleration”
maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether
i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis
melhor prompt do dia:
Based on everything you know about me, roast and don't hold back. Say it in Portuguese slang
Just like this, but add way more português swear words
😂😂😂😂
Jonata Santos retweeted
Sabi Trust Center is coming along nicely.
trust.meetsabi.com
Making great progress on SOC 2 Type 2 assertion...
Leveling up!
One moment, you wrote the last line of code without realizing it was the last line you would ever write by hand
the new Herdr machines is great!
you can see all your agents working independently, regardless of where they’re running
see all your vps and local agents in the same place
Jonata Santos retweeted
Jason Fried's X post inspired us to add a weekly AI customer-sentiment report. Here's how I implemented his process for Sabi and customers.
Jonata Santos retweeted
Inspired by this post from Jason.
Wrote up how we implemented this idea for 2 projects this week.
inovo.io/posts/weekly-custom…
Agent Clawdito automatically writes up customer sentiment analysis weekly, summaries monthly, and posts it back to Basecamp in the dedicated Customer Sentiment project. It also creates its own cards to track on the "What Keeps Happening" Card Table, creates its own to-dos, and posts occasional summaries in the Chat.
It also wrote up a report explaining what runs and when. The report is stored in the project as well so there's a perpetual reference to the methodology and approach. Finally, it wrote up a guide for how to interpret the "State of the Customer" reports. This doc covers things like the sentiment scale, frustration tiers, and everything else we need to know to make sense of it all.
And all of this is stored in a single Basecamp project, all for us humans to see, learn from, follow-up on, and interact with.
Jonata Santos retweeted
Sabi betting table is filling up fast!
1 week projects = 1 deep work session
Ripping through these fast with @steezdiaz and @_jonatasantos
Sabi is here 🔥
An opinionated AI assistant that gives you back time with your family.
100 users have already joined. Check it out 👇
Been working on this for the last few months with my good friend @steezdiaz .
Sabi is an AI assistant built for family-first founders.
Launched this week... just onboarded our 100th today!
inovo.io/posts/meet-sabi-ai-…
