Manu Garg

Creator of @Cloudprober, Pacparser and PageNotes. SRE @ Snowflake, ex-Robinhood, ex-Google. Longer posts: Older:

[Manu Garg @manugarg]

Getting an org to invest in probers is hard. Deciding what to probe is harder.

Most solve it by probing everything — expensive fast, and it ends with a fleet nobody trusts.

Probe systemic issues and critical user journeys. Not every feature.

https://t.co/jPgAFq60b6

[Don Pettit @astro_Pettit]

My best shot of the 2025 Prayag Maha Kumbh Mela from ISS. It is a once in a 144 year Hindu pilgrimage to sacred riverbanks in India and one of the largest events in the world, with millions of people in this single photo!

[Manu Garg @manugarg]

2/ I used only xhigh reasoning mode for PR reviews, and Qwen3.8-27B does like to use a lot of tokens in xhigh mode. When I was running it with ~82k context length during benchmarking, opencode had to compact the context during a couple of longer sessions.

[Manu Garg @manugarg]

1/ About the model itself - so far based on my experience of using it with OpenCode, hype seems justified - I used it for a few @cloudprober and Page Notes PR reviews, & compared review depth and speed with what I see on Opus 5. No hard numbers but model performed almost on par.

[Manu Garg @manugarg]

@smritiirani So very well put!

[Manu Garg @manugarg]

@mishra_pankajk haha, of course. The thing is Jeff is not flashy but he is very effective and he has been consistently right about technology trends. Anybody would bet money on this team :-)

[Manu Garg @manugarg]

This is massive. These are the people who have had the most impact on the technology landscape today.

[Jeff Dean @JeffDean]

Announcing Discovery Loop!

I am very excited to announce that, along with my longtime friends and collaborators @Sanjay_Ghemawat, @OriolVinyalsML and @quocleix, we are founding Discovery Loop (@DiscoLoopAI), a Public Benefit Corporation whose mission is to automate machine learning, science, and engineering to accelerate discoveries and progress. The four of us have worked together for 14 to 30 years, and have helped build some of the world’s most used products, infrastructure and AI models, and we’re excited to turn our attention to this ambitious endeavor.

♾

Learn more at: https://t.co/Rv3LMdLluK

[Manu Garg @manugarg]

@JeffDean Jeff, you built Google's foundation & inspired a whole generation of distributed systems. For me, you embody the best kind of genius—creating massive technological impact but always caring.

Good luck on the new adventure! 🚀🚀

[Manu Garg @manugarg]

Wow, that was crazy. Scary stuff. Hope the guy recovers soon.

[Molly Ploofkins @Mollyploofkins]

A tourist was seriously injured Friday evening after being thrown 8 feet into the air by a bull bison in Yellowstone National Park. Professional photographer Mike Macleod filmed the incident and said the bison was "angry, agitated and charging anything and everything." (No audio)

[Sundar Pichai @sundarpichai]

With just one year in orbit, the first FireSat satellite has already spotted wildfires invisible to existing satellites. After a successful launch early this morning, 3 more satellites joined the constellation, bringing us one step closer to our ultimate goal of near real-time wildfire updates every 20 minutes.

Thanks to @EarthFireAll @MuonSpace @MooreFound @BezosEarthFund for the partnership, & @SpaceX for the ride up!

[Manu Garg @manugarg]

This post has touched a nerve for many people in the SF Bay Area. It's hard to imagine / believe if you're not part of this, but much of this rings true.

People who are saying that people earning so much should not complain should understand this -- where you live is your operating system; you pretty much don't have a choice. Before someone says it -- yes you always have a choice to leave the place and move on but OS makes it hard.

[Deedy @deedydas]

The vibes in SF feel pretty frenetic right now. The divide in outcomes is the worst I've ever seen.

Over the last 5yrs, a group of ~10k people - employees at Anthropic, OpenAI, xAI, Nvidia, Meta TBD, founders - have hit retirement wealth of well above $20M (back of the envelope AI estimation).

Everyone outside that group feels like they can work their well-paying (but <$500k) job for their whole life and never get there.

Worse yet, layoffs are in full swing. Many software engineers feel like their life's skill is no longer useful. The day to day role of most jobs has changed overnight with AI.

As a result,
1. The corporate ladder looks like the wrong building to climb.
Everyone's trying to align with a new set of career "paths": should I be a founder? Is it too late to join Anthropic / OpenAI? should I get into AI? what company stock will 10x next? People are demanding higher salaries and switching jobs more and more.

2. There’s a deep malaise about work (and its future).
Why even work at all for “peanuts”? Will my job even exist in a few years? Many feel helpless. You hear the “permanent underclass” conversation a lot, esp from young people. It's hard to focus on doing good work when you think "man, if I joined Anthropic 2yrs ago, I could retire"

3. The mid to late middle managers feel paralyzed.
Many have families and don't feel like they have the energy or network to just "start a company". They don't particularly have any AI skills. They see the writing on the wall: middle management is being hollowed out in many companies.

4. The rich aren’t particularly happy either.
No one is shedding tears for them (and rightfully so). But those who have "made it" experience a profound lack of purpose too. Some have gone from <$150k to >$50M in a few years with no ramp. It flips your life plans upside down. For some, comparison is the thief of joy. For some, they escape to NYC to "live life". For others still, they start companies "just cuz", often to win status points. They never imagined that by age 30, they'd be set. I once asked a post-economic founder friend why they didn't just sell the co and they said "and do what? right now, everyone wants to talk to me. if i sell, I will only have money."

I understand that many reading this scoff at the champagne problems of the valley. Society is warped in this tech bubble. What is often well-off anywhere else in the world is bang average here.

Unlike many other places, tenure, intelligence and hard work can be loosely correlated with outcomes in the Bay. Living through a societally transformative gold rush in that environment can be paralyzing. "Am I in the right place? Should I move? Is there time still left? Am I gonna make it?" It psychologically torments many who have moved here in search of "success".

Ironically, a frequent side effect of this torment is to spin up the very products making everyone rich in hopes that you too can vibecode your path to economic enlightenment.

[Manu Garg @manugarg]

Anthropic is hell-bent on giving away its early lead to OpenAI. What's even worse is the corporate-speak in this post -- trying to trick people into believing they are getting something, while they're losing ability to use their sub for so many things.

[ClaudeDevs @ClaudeDevs]

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage.

The credit covers usage of:
- Claude Agent SDK
- claude -p
- Claude Code GitHub Actions
- Third-party apps built on the Agent SDK

[Manu Garg @manugarg]

@anoopcj haha.. I have serious doubts 😂

[Manu Garg @manugarg]

More than 6 months later and even after Opus and OpenClaw revolution, this post still holds true.

I use LLMs all the time and agree that the progress is very real, but I sometimes end up spending too much time on getting a good design out of them -- they sound so convincing and so close that it's hard to stop 😂

I need to remind myself of this post from time to time.

[Manu Garg @manugarg]

Over-relying on LLMs will slow you down instead of speeding you up.

[Gabbar @GabbbarSingh]

It’s very difficult with Democracies to deal with Trump.

Democratic leaders can’t openly boot-lick him, let go of nation’s self esteem, without hurting their voters. Unfortunately, that’s the only strategy that works with Trump. Dictators, Authoritarians work really well with Trump as they don’t face any elections, even if they do, they steal it. Trump secretly envies the dictators for managing their press. He wants to do the same, shut the failing New York Times, hates the late night shows who make a killing joking about him, but he can’t.

Hence, Democracy is a handicap till Trump is around. Wait it out.

[Manu Garg @manugarg]

@jonallie I've not tried opencode and other LLMs yet. Seeing a lot of good reviews of GLM 5.1 lately. Thinking of giving it a try with opencode and openclaw/hermes (another thing I've not tried at all yet).

[Manu Garg @manugarg]

. @antigravity has become so good I find myself using it over Claude Code for many things.

[Manu Garg @manugarg]

Introducing Browser Probes in Cloudprober 🚀
https://t.co/MAriFgELnW

Under the hood, Browser Probes run headless Chrome via Playwright, wrapped in a production-grade harness:

- First class metrics + alerting -> Prometheus, OpenTelemetry, CloudWatch, etc as well as native alerting. Step-level success & latency, not just pass/fail.
- Built-in Triage UI: Screenshots, traces, and reports -- filterable by time range and failures for quick incident triage.
- Managed Artifacts: Automated artifacts lifecycle management + async uploads to S3, GCS, or Azure Blob Storage. You don't need another process to manage the disk space.
- Production-grade reliability: Runs inside Cloudprober’s proven scheduling and execution framework.

Visit https://t.co/vKUTHfhRbh for a live demo.