Carlos 'Los' De Santiago

Señor dev, 2x founder, background in fashion + science, 🇲🇽 immigrant. Prev: team lead @Bloomtech ,@StartupSchool '17, CEO at Buymeby, @Stanford '12

[Carlos 'Los' De Santiago @HeyClos]

Anthropic’s February 2026 update means new prompting strategies & less time staring at output that’s almost right but not quite.
https://t.co/C007iHV2Sr

[ₕₐₘₚₜₒₙ @hamptonism]

HydraDB solves the amnesia problem in AI agents: one API for persistent sessions and shared memory that compounds over time (92% recall in <200ms).

[Glen Allsopp 👾 @ViperChill]

@vadymhimself @timsoulo @ahrefs From the study, "To clarify, “YouTube mentions” refer to any time a brand name crops up in a YouTube video title, transcript, or description"

Lots more insights in the full reports 🤝

https://t.co/Br2NejZV5i

[Carlos 'Los' De Santiago @HeyClos]

@ProfAdebay @danjones @DavidFrosdick @levelsio @Tailscale @Hetzner_Online @claudeai @Cloudflare @TermiusHQ Thanks for the thoughtful response! Thought this might be the case!

[Carlos 'Los' De Santiago @HeyClos]

@levelsio Creator forgot to log out of their creator account & commented:
"I signed up for updates on this ages ago and nearly screamed when I saw the Kickstarter went live.
Can’t wait to translate my dog. I’m fully prepared for him to just be saying “ball? ball? ball? ball?” on repeat 😂"

[Carlos 'Los' De Santiago @HeyClos]

@danjones @DavidFrosdick @levelsio @Tailscale @Hetzner_Online @claudeai @Cloudflare @TermiusHQ Could Cloudflare tunnels play a role in mitigating the issues here in any way?

[Carlos 'Los' De Santiago @HeyClos]

@elonmusk So cool. What's the "sludge" byproduct disposal process like?

[Alvin Sng @alvinsng]

One of my favorite superpowers of agents is building classifiers. It’s insanely high leverage.

Before AI, you needed a year-round team:

- 3 ML engineers to build the models
- 3 ML infra engineers to scale them up
- 2 software engineers to integrate the parts
- 1 data scientist to analyze it
- 1 PM to manage the product
- 0.5 EM to hold it together

Now, in minutes, you can have an agent generate a markdown file that classifies inputs, then let agents run continuously against it.

Below is a Sentry error classifier I generated at @FactoryAI. But you can build this for almost anything: customer-reported bugs, backend traffic analysis, fraudulent payment activity.

Personal use cases too: categorizing credit card transactions, labeling emails, or organizing documents.

[Carlos 'Los' De Santiago @HeyClos]

@kaaaash____ “For the simplicity that lies this side of complexity, I would not give a fig, but for the simplicity that lies on the other side of complexity, I would give my life.” - Oliver Wendell Holmes

[Carlos 'Los' De Santiago @HeyClos]

@hridoyreh can you turn this into a huge article and add 🚨🚨 all over

[@levelsio @levelsio]

My laptop screen looks pretty much like this all day now and same on my iPhone when I work (which could be anywhere now)

It's just tabs for my sites, all on a VPS, synced with my iPhone via @TermiusHQ (unaffiliated) and usually with Claude Code open to fix or build new things

[Dan Hightower @Danhightower]

Founder hack: form a startup as an LLC first, then convert to a C‑corp once the LLC is worth several million (but under the QSBS $75M cap) so that the higher fair market value becomes your “basis” for QSBS and you can exclude up to 10x that amount from federal tax on exit, potentially turning hundreds of millions of gain into 0%-tax QSBS instead of being limited to the flat $10–15M cap. You're welcome have a good weekend.

[@levelsio @levelsio]

So here's my latest set up

Every site I have is a profile on Termius like

> hoodmaps .com

I click it and immediately I'm in my server and I get dropped in a tmux session that's always tied to the corresponding site I wanna log in to

To make this work I have this startup snippet in each site's Termius profile:

> cd /srv/http/hoodmaps.com && tm

(so /srv/http is where my sites are and then hoodmaps .com is the example site here, and "&& tm" is the important part here)

Then in my ~/.bashrc file I added this (written by Claude Code) which defines the "tm" function, again all it does it just put me in the right tmux session based on the folder I'm in

The result is I can switch without interruption from my laptop to phone in Termius with auto reconnecting sessions and usually I just have Claude Code open in each session to work

Before I had to mess around with 1) not having smooth switching from laptop to phone, I'd have to use Claude Code's /resume for it, annoying, 2) having multiple sessions for same sites, gets messy and confusing fast, now it FORCES me into one session per site, this just works so well, I'm so fast, and each of my sites is just an open tab in Termius, I've never worked so structured and clean!

Here is the code, maybe it helps somebody:

# tmux session per folder. `tm` (no args) attaches to / creates a session
# named after the current dir's basename. `tm name` overrides the name.
# Works whether already inside tmux (uses switch-client) or outside it.
tm() {
command -v tmux >/dev/null 2>&1 || { echo "tmux not installed"; return 1; }
local name="${1:-$(basename "$PWD")}"
# tmux session names can't contain '.' or ':' — replace with '-'
name="${name//./-}"
name="${name//:/-}"
if [ -n "$TMUX" ]; then
tmux has-session -t "$name" 2>/dev/null || tmux new-session -d -s "$name" -c "$PWD"
tmux switch-client -t "$name"
else
tmux attach -t "$name" 2>/dev/null || tmux new -s "$name" -c "$PWD"
fi
}

# Auto-attach on interactive login: picks a session named after wherever
# you land. Plain `ssh server` lands in $HOME → session "root". Use
# `ssh server -t "cd /srv/sm.levels.io && bash -l"` to land in a site
# folder → session "sm-levels-io". Skips inside tmux and non-interactive
# shells so scp/rsync/scripted ssh keep working.
if command -v tmux >/dev/null 2>&1 && [ -z "$TMUX" ] && [[ $- == *i* ]]; then
tm
fi

[Carlos 'Los' De Santiago @HeyClos]

turbovec + DwarfStar 4 🤝

[Nattu @reallynattu]

Things GitHub READMEs do that I keep forgetting:

- animated SVGs
- mermaid diagrams
- LaTeX math
- collapsible <details>
- direct video upload

Now I want to redo every repo.

[Aaron Levie @levie]

Great post on FDEs. Everyone should read it if you’re interested in this job category. This is a job that is going to be around as long as AI keeps changing rapidly, which it inevitably will.

People often wonder why isn’t this like just deploying other forms of technology in the past, like cloud.

Because something like cloud adoption affected a fairly concentrated set of users (developers and IT), and generally didn’t require a fundamental change to the workflows of employees to get the benefits of the new service being delivered on the cloud. At best you went to one training session and you were done.

With agents, the work to implement them is not only highly technical, but they directly impact the underlying workflows that people participate in. This means there’s a ton of technical work and change management that comes with it.

Further, the pace of change of cloud wasn’t nearly as quick, so there was a lot more time for best practices to propagate. Now, every model change means either something new can be done that wasn’t possible before, or some piece of scaffolding is now redundant or holding you back.

This is why it’s commonly easier for a vendor or partner that’s seen the implementation hundreds or thousands of times help do the work, even with internal support from the customer.

So, this job isn’t going away any time soon, and will be a great path for a lot of technical talent, especially early career.

[Jaid @JaidCodes]

@github

[Carlos 'Los' De Santiago @HeyClos]

@kirodotdev excited to take it for a spin!

[Carlos 'Los' De Santiago @HeyClos]

@MrKryptonBTC @kirodotdev hahah on Opus 4.7? Work took 5x as long 2 nights ago thanks to these errors, had to switch models unfortunately. I'm confident they're an industry-wide issue tho

[Carlos 'Los' De Santiago @HeyClos]

@glcst @sarmag77 @pavan4820 8 away

[@levelsio @levelsio]

A nice way to stay safe is to ask Claude Code to audit your devices

I do same on my VPS servers, so today I tried it on my MacBook Pro and it's pretty good at it too

It founds lots of stuff that was not secured, I actually forgot to enable FileVault when I got this new MBP in 2025, also some local networking stuff

Just ask it "can you security audit my computer"