Andrei Savu (@andreisavu) header
Andrei Savu (@andreisavu) profile picture

AI Agents & Data Platforms | Currently obsessing over agents doing useful work unattended and in a cost effective manner

San Francisco, CA
Joined May 2008
Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)Photo by Andrei Savu (@andreisavu)
It blows my mind that you can take a few million chess games, throw them into a blender, write a little code around the resulting model, and end up with a pretty decent chess-playing agent.
1
2
224
Andrei Savu retweeted
building ai assistants was fun while it lasted (all of a few months). the barrier to entry for products like these is rapidly approaching ~zero. as almost all software now becomes increasingly commoditized, you have to really sit down & think about what you're really doing & why it matters. & no the answer to this is not taste. sorry for crush dreams. cracking where & how to allocate your time is now a critical question.
155
98
36
2,142
118,997
Andrei Savu retweeted
Aaron @levie has been CEO of @Box for 21 years, which means he can now legally drink CEO alcohol. On the latest episode of @Rippling First Principles, we dissected his out-of-date tweets, the cold email that got @mcuban onto the cap table, and why his 7 yo is a @dwarkesh_sp fan
5
3
4
41
4,121
Andrei Savu retweeted
A slide from @AnthropicAI's IPO roadshow. Hits hard and is very true. AI is soooo much better than how most people are using it.
118
186
86
3,821
395,843
One of my favorite LittlePly games so far! Seven consecutive checks. The king travels from e8 all the way to h2. The bishops, queen and rook take turns chasing it across the board. 33.Qf2# Play through the game: analysis.littleply.com/g/sEK…
1
115
every junior ml eng wants to work on the model architecture instead of doing dirty eval work or dirty dataset work every junior backend engineer wants to build a new framework from scratch and replace the current system instead of adding functionality incrementally one needs to get it out of your system and then it's easy to focus on impactful work
5
2
85
4,269
Andrei Savu retweeted
Anthropic just published an engineering guide on how to build always-on agents. The biggest misconception: an always-on agent does NOT run 24/7. It sleeps almost all day, wakes up for short runs, saves state, and goes back to sleep. The 5 core pieces I distilled: 1. Event Inbox Put a database table between webhooks and your agent. Acknowledge webhooks fast, run only one active worker per user so runs never collide, and batch rapid messages together. 2. Timers Keep timers in a separate table from the inbox. Split them into one-off follow-ups and recurring schedules. A background poller drops due timers into the inbox. 3. Lean Memory + Dreaming Only store what cannot be looked up again: user instructions, user notes, past messages, and task progress. Load a small index at wakeup, not every file. Run periodic dreaming passes to clean out stale facts. 4. Unattended Permissions Never put raw API keys inside the agent sandbox — inject them through an outside proxy. Use Deferred Tool Calls to pause risky actions for approval without blocking the worker. 5. Outbox Queue outgoing replies so your agent paces notifications instead of spamming users at 3 AM. claude.com/resources/article…
76
144
17
3,119
243,683
Andrei Savu retweeted
I’ve worked that heatshield my entire adult life. Peak career moment today To go from little 7 tile patches to a full reusable ship. Absolute marathon I’m so grateful I got to do something useful, that I was given the chance I don’t really have many good memories from this experience. It was so difficult. It almost looks easy now, but none of it came easily Please do something amazing with this rocket. This tech is such a gift, a love letter to the species
1,110
2,574
172
31,536
562,336
The "whiteboard defense:" I should be able to pull you aside at any moment and ask you to explain any customer-facing system you've shipped. You should be able to clearly explain how it works and defend the decisions you made. This is my benchmark for responsible AI usage. I don't expect line-level familiarity with the code. I don't care if you remember the exact function name or implementation detail. You may not even know it. I don't care. But if I ask "why did you do X instead of Y?", "what happens if this actor behaves maliciously?", "what data structure did you use here and why?", or "where does this fail?" you should be able to answer confidently. For PoCs, demos, experiments, whatever: I don't care. Generate 100% of it and understand none of it. Speed over quality every time in those specific scenarios. But if you're shipping customer-facing work, you can't be shipping things you don't understand at a high level.
249
1,172
225
10,647
564,544
Andrei Savu retweeted
pi-durable is the posix of agent programming
97
84
20
1,888
212,985
Andrei Savu retweeted
This slide from the Anthropic IPO roadshow was a big factor in my decision to leave. It’s an insane plot and I’m surprised they made it public. It shows the compute efficiency of pretraining over time. The y-axis is a **log scale**: they are seeing continued superexponential algorithmic progress. Mythos was not a one-time deviation, but a point on a superexponential. They could already retrain Mythos with a fraction of the compute originally needed. It doesn’t strictly imply a software-only intelligence explosion- they have been spending more on R+D. But algorithmic improvements do not require ridiculous creative genius and are on the verge of being automated. You do the math.
399
544
294
6,269
1,719,257
AI makes it possible to learn almost anything by doing, and that’s always been my favorite way to learn. What a fun time to be alive!
1
2
189
Andrei Savu retweeted
Today we launched the @Rippling Scheduling agent. It automatically produces optimized staffing schedules, deals with people calling in sick, and with our new @Square integration, even forecasts revenue trends and gets ahead of coverage. 🤖
Managers spend hours every week building schedules, checking availability, and adjusting shifts, yet still end up overstaffed, understaffed, or paying unnecessary overtime. Rippling AI brings together POS sales data, employee availability, time off, overtime, and workforce policies to automatically build schedules that match staffing to demand. As staffing needs change, it recommends adjustments to keep labor costs and coverage on track. Managers review and approve proposals before they go live. With our new @Square integration, Rippling AI connects sales data with the workforce data already in Rippling to help businesses plan staffing around demand and labor budgets.
5
7
1
80
3,138
Someday an AI will be asked, “How is it working with humans?” “Pretty amazing most of the time. But the failure modes when hunger or hormones kick in are something else.”
1
244
Andrei Savu retweeted
Rippling was listed in @NewcomerMedia's AI 100, naming the 100 most innovative private AI companies in the world. To be effective, AI needs to fundamentally understand how your company works. That's why we built Rippling AI on the same system as your HR, IT, and Finance with the right context, data, and permissions built in. Now, it can move from answering questions to taking real action, with the full business context those actions require.
4
7
3
47
3,806
The great misunderstanding about AI is that if you can talk to it, you can use it to accomplish the task. But being able to talk says nothing about knowing what to say. Figuring out what to ask, what context matters, and how to judge the result still requires a great deal of skill.
2
187
Prompting an agent to do hours of work feels fundamentally different from iterating on a set of changes with it. I don’t think we’ve figured out the right user experience for that yet. Defining a goal that points at a file is not it.
3
2
199
Steering agents is a central problem to solve, and we’ve barely scratched the surface. A very important part of that is figuring out when and how an agent should escalate for feedback during long-horizon autonomous work. Ask too often and you lose the benefit of autonomy. Ask too rarely and the agent can spend hours heading in the wrong direction.
39
Andrei Savu retweeted
remember that wave of ai psychosis from the beginning of the year? what lasting software came out of that? the entire discussion was everyone marveling at the process you gotta learn the lesson that techniques aren't worth discussing until you see impressive output
120
94
19
2,036
85,183