Control Alt

recovering perfectionist, action beats overthinking, stretching my comfort zone

"Imperfect action beats perfect inaction every time", Alex Hormozi

[Control Alt @ctrl_alt_focus]

registrations are open 🔥
for @AlexHormozi 's $100M Money Models book launch
it's august 16th, 100% free
https://t.co/hzgOG6X9ZV

he's teaching how to get customers to spend more money
giving away a secret project he's worked on for 4 years (but only to people who show up live)

[Josh Kale @JoshKale]

This is big... Anthropic just announced a model so powerful they won't release it to the public out of fear over the damage it will cause 😨

Claude Mythos Preview found thousands of zero-day exploits in every major operating system and web browser...

The numbers are hard to believe:
> $50 to find a 27-year-old bug in OpenBSD, one of the most security-hardened operating systems ever built

> Under $1,000 to find AND build a fully working remote code execution exploit on FreeBSD that grants unauthenticated root access from anywhere on the internet

> Under $2,000 to chain together multiple Linux kernel vulnerabilities into a complete privilege escalation exploit

For context: these are the kinds of findings that previously required elite security researchers working for weeks.
Anthropic engineers with no formal security training asked Mythos to find exploits overnight. They woke up to working code the next morning.

The results were so impressive Anthropic assembled Apple, Google, Microsoft, Amazon, NVIDIA, and seven other organizations into Project Glasswing:

A $100M defensive coalition. They're not releasing this model publicly. Instead, they're racing to patch the world's infrastructure before models like this proliferate.

[Ashpreet Bedi @ashpreetbedi]

Maybe I'm missing something, but "harness engineering" might be doing more harm than good.

I've read a couple of posts on harness engineering, filesystem memory, subagent architecture. All real, all important. I've learned a lot from them.

But I keep coming back to this: the framing of Agent = Model + Harness undersells the actual engineering involved. And as far as I can tell, none of the major agent products work this way.

Claude, ChatGPT, Devin. These are all systems. They handle authentication, multi-tenancy, deployment, observability, cost controls, state management across sessions and users, RBAC, resource isolation. The "harness" is a subset of the engineering involved in building these products.

A better framing might be Agent = Model + System. This makes sense because you can't serve a raw API call to users. You need the system around it to turn the model into a product. You could argue Agent = Model + Harness + System, and that's fair. But at that point the harness is just a component of the system. Treat it as one.

My concern is that when we center the conversation on harness engineering, we train developers to think about the 30% that touches the model and ignore the 70% that makes the thing actually work in the real world.

When we look at the problem through the lens of the 30%, we end up with things like virtualized file systems which are solving problems that shouldn't exist in the first place.

At best, the harness wraps the model. The system is the product. And there's a reason the consensus is that model progress will eventually swallow the harness. Because the harness is a thin layer. The system is not. The system is the product, and that's what developers should be focusing on.

Another reason to take harness engineering with a grain of salt: it's shaped by coding agents. Coding agents are a very specific form factor which itself is evolving rapidly. Single user. Running in a terminal. Local filesystem. The patterns that emerge from this form factor are useful for this form factor. And I worry that generalizing them to broader agentic systems is damaging to the ecosystem as a whole.

Here's what I mean. And notice a pattern: many of these are solutions to problems that shouldn't exist in the first place if you start with the right system design.

1. Filesystems for memory and storage
Harness engineering recommends patterns like AGENTS.md files for memory. This works when one developer is running one agent on their laptop. It falls apart the moment you need a real product. There's a reason databases exist. Files don't support concurrent access. They don't support querying. They don't support access control. A filesystem as your memory layer is a single-user solution presented as architecture.

And now I'm seeing people build "virtualized file systems" that wrap databases into filesystem-like structures to patch over these limitations. At that point, just expose the database. You get SQL as a first-class interface, proper access control, and durable storage without the abstraction gymnastics. And you know what, LLMs are even better at SQL than they are at cat and bash.

2. No multi-tenancy or RBAC
How do 50 engineers on a team share an agent securely? How do you control which users can trigger which actions? That's multi-tenancy, authorization, and access control. No filesystem pattern solves this. You need real RBAC.

3. No resource isolation
How do you stop one tenant's runaway agent from burning through your entire token budget? That's resource isolation. It lives at the system level. A harness has no concept of it. I hear people recommending sandboxes scoped to individual users and it makes 0 sense to me because your costs will eat you alive.

Btw these problems aren't new. They're the same problems we've been solving in software engineering for decades.

The instinct to create new terminology comes from a good place. "Harness engineering", "Scaffolding”, "Context engineering". People want to name the new discipline. But every time we mint a new term for a subset of systems engineering, I think we make it harder for developers to recognize that the patterns they need already exist and we shouldn't re-invent the wheel.

All problems that harness engineering solves, you can solve with systems engineering. Maybe I'm wrong about this, but I'm just seeing harness engineering create more issues than it solves (virtualized file systems???)

If we want developers to successfully build agentic products, we should encourage them to think in systems. The solutions already exist. We should use them.

Again, maybe I'm missing something. I'll keep an open mind as I learn more. And maybe the answer is simply that harness engineering applies to coding agents and not to broader agentic products, which makes perfect sense.

TLDR: Agent = Model + Harness undersells the real problem. Harness engineering is shaped by coding agents (single user, terminal, local filesystem) and ignores the 70% that makes agents work in production: multi-tenancy, RBAC, approval flows, audit logs, resource isolation, durable storage.

These are systems engineering problems.

[Control Alt @ctrl_alt_focus]

@ashpreetbedi nicely written

although for me TLDR is FOMO
i mean kind of that there's lots of (existing/new/wannabe) influencers creating FOMO

but am glad to see someone explain it the way you do, in detail 😄

[Control Alt @ctrl_alt_focus]

@kvnkld nice UX! and animations are neat!

how do you prompt it to get proper animations without too much back and forth?

[Control Alt @ctrl_alt_focus]

@yorgohoebeke persistent notifs, nice idea!

[Control Alt @ctrl_alt_focus]

@GergelyOrosz @grok what IS on his bingo card?

[Control Alt @ctrl_alt_focus]

@muongas @GergelyOrosz @grok i use claude cowork, it works really well
better than perplexity's comet browser or openai's one

which one do you use, and what problems have you had with claude desktop co-work?

[Pavel Durov @durov]

Today, Telegram notified all its users in Spain with this alert:

Pedro Sánchez’s government is pushing dangerous new regulations that threaten your internet freedoms. Announced just yesterday, these measures could turn Spain into a surveillance state under the guise of “protection.” Here’s why they’re a red flag for free speech and privacy:

1. Ban on social media for under-16s with mandatory age verification: This isn’t just about kids—it requires platforms to use strict checks, like needing IDs or biometrics.

⚠️ Danger: It sets a precedent for tracking EVERY user’s identity, eroding anonymity and opening doors to mass data collection. What starts with minors could expand to all, stifling open discourse.

2. Personal and criminal liability for platform executives: If “illegal, hateful, or harmful” content isn’t removed fast enough, bosses face jail.

⚠️ Danger: This will force over-censorship—platforms will delete anything remotely controversial to avoid risks, silencing political dissent, journalism, and everyday opinions. Your voice could be next if it challenges the status quo.

3. Criminalizing algorithm amplification: Amplifying “harmful” content via algorithms becomes a crime.

⚠️ Danger: Governments will dictate what you see, burying opposing views and creating echo chambers controlled by the state. Free exploration of ideas? Gone—replaced by curated propaganda.

4. “Hate and polarization footprint” tracking: Platforms must monitor and report how they “fuel division.”

⚠️ Danger: Vague definitions of “hate” could label criticism of the government as divisive, leading to shutdowns or fines. This can be a tool for suppressing opposition.

These aren’t safeguards; they’re steps toward total control. We’ve seen this playbook before—governments weaponizing “safety” to censor critics. On Telegram, we prioritize your privacy and freedom: strong encryption, no backdoors, and resistance to overreach.

✊ Stay vigilant, Spain. Demand transparency and fight for your rights. Share this widely—before it’s too late.

[Yuchen Jin @Yuchenj_UW]

@willIsbillls

[Control Alt @ctrl_alt_focus]

@timo_rf @ivanburazin @daytonaio used grok to show that even if you're short on time or imaginatiok or empathy, if you wanted to you easily could have

[Control Alt @ctrl_alt_focus]

@timo_rf @ivanburazin @daytonaio examples of how to share the same message with empathy and supportive wording so that people who need a push get the push and the others see an imsight but get a break (literally and figuratively)

[Control Alt @ctrl_alt_focus]

@JaySym_Ai @igoro related question, i don't see credit usage in the web analytics ui. Is that because it is free for now?
Is there a way to view pr at least estimate credit consumption or is the amount of credits consumed for context engine usage still not fully fixed on your end?

[Control Alt @ctrl_alt_focus]

@igoro oh sweet, nice example 🔥

[Control Alt @ctrl_alt_focus]

@Xx17965797N ai gen keeps blinking

why not just use your own voice 🫠 with text..

[Naughty Beaver @beaver_naughty]

Amazon just fired everyone in Quebec & shut down all warehouses because they unionized. There is no way in hell that companies like that are building robots & AI because they want to liberate humanity from slavery.

[The Architect. @TheMarcitect]

Does anyone really believe when AI and androids take over they are just going to let us all do what we want.. billions of people without jobs and nothing to do. Trust me there's a future for the rich and it's a future without us. A big drop in the worlds population is coming.

[Control Alt @ctrl_alt_focus]

@igoro @JaySym_Ai @augmentcode @zeddotdev @GitHubCopilot @kilocode interesting, curious to try it out for sure 🙌

[Control Alt @ctrl_alt_focus]

@igoro @JaySym_Ai @augmentcode @zeddotdev @GitHubCopilot @kilocode @GosuCoder been seeing Morph proposing context as an MCP service
now augmentcode

would you consider comparing a model in for example cc, cc with augmentcode context mcp, cc with morph context mcp ?
(i think it was called morph and offered 40million free tokens)

[Control Alt @ctrl_alt_focus]

@JaySym_Ai whennn