Local LLMs will solve this.
506 karma · joined May 19, 2020
You are constructing the set of context, policies, directed attention toward some intentional end, same as it ever was. The difference is you need fewer meat bags to do it, even as your projects get larger and larger.
To me this is wholly encouraging.
Some projects will remain outside what models are capable of, and your role as a human will be to stitch many smaller projects together into the whole. As models grow more capable, that stitching will still happen - just as larger levels.
But as long as humans have imagination, there will always be a role for the human in the process: as the orchestrator of will, and ultimate fitness function for his own creations.
Folks on places like HN should also realize that the broader US is not as liberal as the news and internet would make you think. The people who comment and debate online tend to be on the more extreme ends of both sides.
The rest of us (wisely or not) feel like it's typically not worth the energy to get involved.
Until it is.
The outsized public hatred toward Meta is almost entirely driven by a bureaucratic, anti-technology Europe (that has finally realized that their overstepping is hurting their future) and a US political institution that needed someone to demonize to keep us all distracted.
There are very good reasons to dislike Meta and Meta products. But they're likely not the ones you're referring to.
Like, literally building smart homes.
Locally intelligent in ways that enable truly magical smart home experiences while preserving privacy and building trust.
But connected in ways that facilitate pseudo-social interactions, entertainment, and commerce.
Meta's biggest competitors are Apple and Amazon. This is the first clear opportunity they've had to leapfrog both.
It's actually potentially harmful that current AI email assistants try to impersonate their users. When these systems are designed to write as though they're you - using your voice, your style, your signature - they create a kind of social deception that undermines genuine human connection.
Consider what happens when you meet someone after your AI has "written as you" in an email exchange. They might reference specifics from "your" message that you have no actual knowledge of. You're supposedly continuing a conversation you never actually had. This creates an awkward disconnect that erodes the authenticity of human interaction.
In our rush to make AI communications feel natural by mimicking human writing styles, we risk something more valuable: genuine connection. The problem isn't just that current AI systems don't sound enough like us (Koomen's concern), it's that they're pretending to be us at all.
A more honest and ultimately more useful approach would be for AI agents to have their own distinct identities: "Sent on behalf of Mason" or "Read on behalf of Sarah." This transparency preserves both the utility value of efficient communication and the personal value of authentic human interaction.
For AI-mediated communication to truly succeed long-term, we need to separate:
1. Utility communications (scheduling, information sharing, routine updates)
2. Personal communications (relationship building, creative collaboration, emotional connection)
When we blur these lines by having AI impersonate us for utility communications, we risk devaluing the currency of genuine person-to-person exchanges. After all, part of what makes a personal message meaningful is knowing that another human took time specifically for you.
So while I still believe agent-to-agent negotiation is the future of routine communications, I think transparency about AI involvement is equally (if not more) important. The end state isn't AI that perfectly mimics our writing styles; it's a communication ecosystem where AI handles routine exchanges transparently, while preserving the special value of genuine human connection.
The article focuses on giving users control of their System Prompts to personalize AI outputs, but this approach still assumes a world where humans are both crafting and consuming messages directly. What's missing is consideration of how communication will evolve when AI agents exist on both sides of exchanges.
Consider these scenarios that exist simultaneously during this transition:
- Senders using AI, recipients who aren't
- Recipients using AI to process messages, senders who aren't
- Eventually: AI agents on both sides
In this final scenario, the actual transport format becomes less important. In fact, more formal, verbose messages with additional metadata might be preferable as they provide context for the receiving agent to process appropriately.
Imagine a future where you simply tell your AI, "Let everyone know I won't be in today," and your agent determines:
1. Who needs to be told
2. What level of detail each recipient requires
3. What context from your calendar/activities is relevant
On the receiving end, the recipient's agent would:
1. Summarize the information based on relevance
2. Determine if follow-up is needed
3. Automatically reschedule affected meetings
Most importantly, these agents could negotiate with each other behind the scenes. If your message lacks critical information, the recipient's agent might query yours for details: "Is this a one-day absence or longer? Are there pending deliverables affected?" Your agent would then provide relevant details without bothering you.
This agent-to-agent negotiation seems far more likely than what Koomen proposes - users meticulously crafting System Prompts to personalize their communications. In practice, most people don't want to configure systems; they want systems that learn their preferences through observation and feedback.
Rather than focusing on making current AI implementations mirror human communication styles more precisely, perhaps we should be designing for the eventual world where AI mediates most routine communication, with detailed configuration being the exception rather than the rule.
The real "horseless carriage" thinking might be assuming humans will remain directly in the loop for routine communications at all.
I also spent a couple hours picking apart Codex with the goal of adding Sonnet 3.7 support (almost there). The actual agent loop they're using is very simple. Not to say that's a bad thing, but they're offloading all planning and workflow execution to the agent itself. That's probably the right end state to shoot for long-term, but given the current state of these models I've had much better success offloading task tracking to some other thing - even if that thing is just a markdown checklist. (I wrote about my experience [1] building AI Agents last year.)
Like you, biggest one I didn't include but would now is to own the lowest level planning loop. It's fine to have some dynamic planning, but you should own an OODA loop (observe, orient, decide, act) and have heuristics for determining if you're converging on a solution (e.g. scoring), or else breaking out (e.g. max loops).
I would also potentially bake in a workflow engine. Then, have your model build a workflow specification that runs on that engine (where workflow steps may call back to the model) instead of trying to keep an implicit workflow valid/progressing through multiple turns in the model.
MCP Commander can manage your configuration files across any host application you have that follows the increasingly-standard MCP server configuration file format.
It sits between your MCP hosts and servers to provide visibility to MCP server traffic.
It lets you configure triggers on MCP server traffic, alarming you to things like tool poisoning attempts, authentication hijacking, stealth commands, data exfiltration attempts, etc.
It lets you easily run certain MCP servers inside of Docker. Configure with one click across all your host applications.
I'm hoping to find beta participants to provide feedback. HN participants will receive a free lifetime license in return.
Turns out, that matters a lot.
Do they know this is what you think of them?
How effective has this attitude been in helping you understand their perspective?
Trying to publicly argue the moral high ground was a stupid, unforced error.
It didn't need to be moralized at all. Just make the changes you want to make, piss off a vocal minority, then get back to winning and making boatloads of money by executing exceptionally.
The problem, I suspect, is that Matt values how certain people perceive him more than he values winning. It's unfortunate, because he's clearly a very good executer and strategist. He's getting in his own way.
If no one you respect has been swayed, you should know: the other side is making the same baffled judgements about you.
A US-based dev directing Claude Code has like 3x output.
So the biz is spending 125 + AI costs, but saving 250/hr.
An individual dev might feel like a superhuman compared to those not using Claude Code. Could even earn them a substantial promotion.
Either way, seems to net out.
I just leave an instruction in CLAUDE.md to validate changes with Playwright. It automatically starts a dev server (wrote a little MCP server to do that), navigates to the page with the changes it just made, and validates that its changes worked. If there is anything unexpected, it self-corrects.
It's like working with a really great mid-level engineer.
What a time to be alive.
I've owned multiple Jeeps in the past.
Never again.
You can write about anything to make it sound bad, even when it's good, and vice versa.
Need to focus on outcomes.
Europe's tech sector will continue to wither as America and others surge ahead.
You can't regulate your way to technological leadership.