Randy Lariar

Head of AI @ Balance Theory. Passionate about tech, business strategies, AI/ML, and dad jokes. Follow me for insights and laughs.

[Randy Lariar @Lariar]

Well this slaps… https://t.co/qS7zxTDwRF

[Kyle 🚄 @KyleTrainEmoji]

PICARD: Data, shields up

DATA: Brilliant! Shields can reduce damage we sustain. Not immunity. Not hubris. Just prudence. It's not precaution—it's strategy.

[camera shakes]

WORF: HULL BREACHES ON NINE DECKS

DATA: Here's what happened: you told me to raise shields, and I didn't

[Randy Lariar @Lariar]

Happy Star Wars day to all those who celebrate

[Seb Goddijn @sebgoddijn]

One of the interesting things we've observed from building glass is that the way to build agents is pretty consistent regardless of team / problem type.

1. Curate some basic context for how to approach the problem, and make sure it has the right tools (mcp, cli, etc) to accomplish its task.

2. Ship it to real users and automate the ability to surface sessions where things went wrong.

3. Run those sessions through a few prompts that generate suggested improvements to the context or tools.

4. Have a human validate those improvements before they go live (at least to start).

Way more effective to put your energy into building the improvement loop than overthinking the perfect v1.

[Chappy Asel @chappyasel]

121 sources. 183 articles. 51 deep-researched repos and papers. Open source, forkable for any domain. Star it to come back later!

https://t.co/t8yeGlirKz

[Randy Lariar @Lariar]

Do I have any new friends in Japan?

[Andrej Karpathy @karpathy]

Software horror: litellm PyPI supply chain attack.

Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords.

LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm.

Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks.

Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages.

Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.

[Randy Lariar @Lariar]

After tinkering with OpenClaw and NanoClaw, I think Claude Code + Telegram gives me everything I need. Going back to my original workflow after a few weeks of diversion, and it all... just works... and is included for $20/month

[Randy Lariar @Lariar]

"the proposed fix mixes a sound diagnosis with an overconfident implementation story."

This is why your vibe coded apps fall over in production

[Matt Prusak @MattPrusak]

Your grandparents had grandparents. They had grandparents. Somewhere back there, someone got on a boat, or didn't. Someone changed their name, or had it changed for them. Someone is buried in a cemetery you've never heard of in a country you've never been to.

Most families lose track after two generations.

I used AI to push mine back nine.

One session with @karpathy's autoresearch pattern: over 100 organized research files. It found a 1940 Norwegian emigrant history with my ancestors in it. Resolved a maiden name question that confused my family for 70 years. Identified relatives no one alive knew existed.

The method is simple: set a goal, measure progress, verify against real records, repeat. The AI searches public archives, cross-references birth certificates against cemetery records against church books, and logs everything it finds (and everything it doesn't).

Open sourced the whole toolkit. Prompts that do the research for you, archive guides for 20+ countries, starter templates, even a framework for making sense of DNA results.

If you have a box of old photos and unanswered questions, this is where to start.

https://t.co/6t4l3hAE1o

[Dan Shipper @danshipper]

guys autoresearch is kind of amazing

it’s also very bitter lesson-pilled:

do away with all of your fancy agent infrastructure. just design the simplest possible system to let you throw more tokens at your problem

[Dan Shipper @danshipper]

this is pretty much the only way to build product in AI

models move so fast, that you have to be willing to throw everything out every few months to take advantage of what's possible

[Manthan Gupta @manthanguptaa]

https://t.co/LeaTneJ9f5

[Randy Lariar @Lariar]

It took me somewhere between six months to ten years to write this.

https://t.co/W9TaNFsAoo

[Randy Lariar @Lariar]

https://t.co/EyRZi7TJbn

[Randy Lariar @Lariar]

https://t.co/EyRZi7TJbn

[Randy Lariar @Lariar]

Who is more bot-like, the bot or the bot-like comment the LinkedIn human writes anyway?

[Lenny Rachitsky @lennysan]

Can't stop staring at this image and thinking about what it means for the future

[Randy Lariar @Lariar]

Score yourself.

8-9: Ahead of 95% of agent operators.
5-7: Fixable. Start with isolation + creds.
3-4: Stop deploying. Harden first.
0-2: That's not an AI agent. It's an open door.

March 9 NIST RFI deadline. Shape the standards or adapt to them.

[Randy Lariar @Lariar]

Your AI agent has more access to your machine than most of your employees.

Shell access. API keys. File system. Network.

Here's how to audit it in 10 minutes. One check per minute. No tools required.

🧵

[Randy Lariar @Lariar]

Minute 9: Has anyone outside your team reviewed the security?

□ Published security audit
□ Bug bounty program
□ CVE response process
□ Independent code review

Zscaler tested AI systems across 9,000 orgs. 100% had critical vulns. Median time to first failure: 16 minutes.