Blixt (@blixt) header
Blixt (@blixt) profile picture

Building @biscuit_so • Previously @Framer, @Spotify

AMS/BCN
Joined August 2007
Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)Photo by Blixt (@blixt)
Pinned Tweet
We’ve been quietly building Biscuit for 8 months. Today we’re opening up the waitlist. Biscuit lets you describe your business idea and we handle everything: product, payments, emails, hosting, going live. You can publish and get your first customer the same day. – at Barcelona, Spain
5
7
2
63
8,206
Blixt retweeted
Marom today built this to increase efficiency in choosing what to have for lunch. Ofc on @Biscuit_so @blixt and @CompuIves we look awesome
1
1
44
join the input waitlist! i've been using input since early beta and you can really feel the artisanal touch behind every feature, interaction, pixel.
Announcing @InputSystems. A new way to email ✨ It handles your messages and the work that follows.
3
11
596
agreed, i caveat gpt feedback very often to opus ("was sol exaggerating", "please check real world uses", "could this happen in practice", ...)
Like a lot of you, I use Opus 5.5 to write code and Codex Astra to review it. But Astra has a bad habit of flagging bugs that are technically possible but 𝗮𝗹𝗺𝗼𝘀𝘁 𝗻𝗲𝘃𝗲𝗿 𝗵𝗮𝗽𝗽𝗲𝗻 in practice. Opus sees the logic checks out and fixes it, then Astra flags the next one, and the loop never stops. Add this line to your review prompt, skill, or AGENTS.md: "Rate each bug from 1 to 10 on how often it would happen and how bad it would be. If the two scores multiplied are below 5, just file it as an issue and leave the code alone." Tune the threshold of 5 to your project. For Opus, the one fixing the code, add one more line to CLAUDE.md or AGENTS.md: "Do not design for rare or future cases nobody asked about."
1
3
274
One of the better phishing attempts I’ve seen lately, watch out for this one. Looks like legit calendly link Redirects to plausible api-cal.com Hides scary permissions below “can see who you follow” etc Chain of failures here, from Calendly and X too!
6
469
Blixt retweeted
Replying to @Biscuit_so
@Biscuit_so team is in such a flow state that we have matching socks at panel events @UvAFounderSpace thanks for hosting us
1
2
2
125
reminder: you can just write 5 words about a problem you have, get a 3d render of the solution, and say "yes" and get a physical product out at the end
9
472
was setting up 5 matter lights from my iphone and with the home app it was a horrible experience of timeouts and lack of information 10 minutes of vibe code and turns out the ux could've been this:
5
15
730
apple's home app doesn't tell you the type of light so you have to guess: turns out detailed info is available immediately upon first scan! the home app doesn't tell you if there's signal, instead it makes you wait 5 minutes: turns out you can just check the bluetooth signal!
1
84
at first i did think it was more than a little awesome there was no bump but then it's suddenly there? now i just think it's a little misleading…
2
42
17,633
if you're building a harness and you decide to put intelligent ui in it then please steal this idea: let the agent design a glance component that renders the same stuff as a single line so i can track the agent's updates from the sidebar
7
4
1
235
14,029
and then make sure you have a nice ios app that has really good realtime sync with all your chats and of course lets you see your favorite glances as widgets
6
1,080
first standup running biscuit on biscuit!
1
2
20
1,075
my agents have taken to saying this a lot lately, i think they're trying to be nice about my time but come on
14
398
…2023: stable pre-ai job 2024: soul searching 2025: ai startup 2026: first 3/4ths look flat because the tail end is up to ~500 commits per day, imo a real inflection point
i wanted to visualize what my github history looked like before and after the AI inflection point. see yours here - mo.rgan.co/gh/ i've looked at a few friends, eng and design, and it's really interesting to see the patterns.
4
16
826
Agents explain things in walls of text. 📃 You ask how a system works, how a bug happens, or what a plan looks like, and you get twelve paragraphs back. So I built ttmi.ai. Your agent draws what it’s explaining instead: youtube.com/watch?v=PSQEYQm7…
1
2
1
10
658
While working on @ClickHouseDB integrations in @Biscuit_so, I wanted to see what you could build on their public playground. This was really fun! Climate stripes for any place on Earth. Up to 122 years of data!
1
2
9
246
Blixt retweeted
There’s always one person who somehow knows everyone. We’re looking for those people. We’re launching @Biscuit_so Ambassadors across Europe. You bring the people. We’ll help with the rest. funny-steam-317.notion.site/…
1
3
107
after all this time, models still can't predict the nuances of shells and operating systems... guess what `pkill -f "codex app-server" -P 1` does on macOS?
1
1
10
685
answer:
3
242