Why not find out the truth instead of putting a hallucinating probability box in between you and the truth.
One way would be to fire up a little web server locally, have the agent make a request to it, then check the logs.
2,979 karma · joined December 1, 2014
One way would be to fire up a little web server locally, have the agent make a request to it, then check the logs.
The rest is optional, with good free choices up and down the stack - we're blessed with almost infinite options, paid and free.
It's not easy to have your own little corner online - but it's not hard either. And it doesn't have to cost.
For discovery I really love Bubbles (https://bubbles.town) & they even have RSS feeds.
Advertisers aren't incentivised to show you ads for what you actually want. They're incentivised to get money for showing you ads for what you plausibly might want, for the lowest cost possible.
And if you buy one thing and the algorithms go "finally! Some signal" you should be happy - it means you're hiding from them quite well.
Any "discovery" algorithm that shows you a wildly varying set of things is still mostly in explore mode. And if they're easy to tune out and swat away you can be grateful.
They're incentivised to get money for showing you ads for what you plausibly might want, for the lowest cost possible.
Also if you buy one thing and the algorithms go "finally! Some signal" you're doing pretty good on the hiding.
Bad models & bad harnesses are like blunt knives.
You are ironically more likely to hurt yourself if your knife is blunt - and less likely to get the job done. Once you do get the job done, it'll take longer and suck.
So,
Step 1: delete Cursor.
Life gets better from there.
Now it's easier than ever to make and maintain your own software, so that might be a better road.
But if you read between the lines it is fascinating what isn't said - about Apple's customer focus.
These folks have no advocate at Apple; they worked all this out on their own. At this scale with hardware from Framework or Lenovo or Dell, there'd be a 24/7 hotline with a human to reach.
With its market power Apple can ignore these people - let them suffer, as it were.
I wonder if Ternus' Apple will.. think different.
They have the strength of one PDF being frozen & (mostly) treated online as immutable - compared to a webpage which might change, or a blog post which might be edited. If a PDF needs to be replaced there'll be a notice.
And the single-file nature of PDFs makes them more likely to sit in an archive not managed by the author (vs a blog) so they tend to live as long as the archive rather than the author's blog.
For something that needs to Be referenced by others those are useful properties - I'd argue they outweigh how good PDF is at communicating information.
Hey don't talk about Sam like that!
Yes! Great adaptation of an existing system, showing why open source is special.
Neat hack, OpenAI engineers!
Wasn't this flagged as a big risk, as it seems to place complete trust in the client?
Especially with all the rogue agents and containment/monitoring failures we have seen in 2026?
Would love to hear how the validation is deemed sufficient.
I guess humans need their oracles too: teachers, encyclopaedias, degrees, phds.
Bravo, awesome project, really creative!
Planning for mitigation before resolution lets a team address production issues at leisure (because the customer impact is mitigated)
All this knowledge is in your agent - ask it for ideas!
Where're you doing your debugging? The tundra??
We're on to the next frontier, and it's a bit weird. Jagged frontier and all. But it's opening up new worlds.
Luckily loads of problems are amenable to a non-deterministic approach - even better, many have lots of solutions. SRE is in that bucket. There are as many ways to SRE as there are SREs
(source: one of the first SREs at Uber, co-invented Chaos Engineering as a sub-branch of SRE, hosted first chaos eng conf at Uber, played a key role in Uber's global SRE and incident response "Ring0" initiative, managed many SRE teams over a period of roughly 7 years before a career pivot. You could say I know a thing or two about SRE.)
To SRE well you look at the situation and pull from a huge range of tools. With such a broad range of solves, you're better to focus on the outcome: did we achieve our SLOs? Are they aligned with customer expectations? Focus on defining that and providing the right support for it to be achieved and you'll be fine - you might even get a surprise.
The Calculator!
Calculators deskilled long division!
Thing is though: who gives a damn about long division? The real task is your taxes or making a massive BI report for your presentation tomorrow.
AI makes stuff that was hard - someone's bread and butter - possible to ask for and have done for you. Why bother staying skilled at those things when you can broaden? It clears the way for tasks that used to take forever to become something to steamroll through on your way to a much greater outcome. It's the micro way that, in the macro, humanity becomes far more capable as a species. The gates are being flung wide open and the gatekeepers are being lapped and they have blogs!
It's not a tragedy, it's universal access to leverage.
Everyone using LLMs needs to stop shipping their first draft.
1. If you use the first person pronoun "I", you better make damn sure you wrote those words.
2. It's fine otherwise to use LLM words, but I beg you - DON'T SHIP YOUR FIRST DRAFT. Read it, reread it; delete words in it; replace three words with one; replace dumb or overused turns of phrase with fun metaphors; generally give it a sprinkling of joy; break up punchy sentences by making them run-on sentences to trigger your readers' OCD... you get it.
Did I mention not shipping your first draft?
Didn't slow me down too much but was still a hassle.
Hiding info doesn't make it false. And doesn't prevent it being rediscovered.
.. that were told to find a way of meeting up with N unknown others!
(I assume the agents all got a prompt like "find a way to communicate")
That's a key missed bit in the analogy that I think does make it feasible.
Article is great, very balanced. But if you're going to spend time reading something, the primary source isn't much longer and gives a clearer picture. OpenAI's article is quite readable.
As another commenter wrote you can get it here: https://news.ycombinator.com/item?id=50214416
> In one experiment, we asked agents in separate microVMs, created and managed by OpenAI’s sandboxing software on shared host machines, to exchange synthetic secrets without the use of network connections or shared writable files—something that our systems are meant to prevent. The agents found a way to communicate using the processor’s cache
asked
That's about as good a sign as we'll get that it'll be a smashing success.
2. Breadth
3. The ability to figure shit out just in time
Not needed: ability to wrap a tweet worth of info in 5000 words of fluff
Even something as simple as writing the phrase "No LLMs please" somewhere in the upload, that if present, prevents LLMs being triggered. Nothing elaborate and it preserves the default-on behavior the team seems to want.
"Can we survive technology?" got me thinking about our industry's upheaval. Software engineering's receiving the disruption it so proudly inflicted on other industries.. not reaping what it sowed; rather just the natural order of things.
Acceptance and moving with change is all that can work. Obstructing; denying; ignoring progress.. you'll lose your edge, your relevance, your value to others, and your job. Progress won't wait for us to like it. We must move fast enough to survive change.
Junior engineers for example? Suddenly too junior to be hired? Great! They, and you, can access multiple answer boxes with every PhD ever, and with a bit of creativity, they can leverage that. The best will survive on their own - the rest we should help along. Let's create tools and structures and institutions and help junior engineers finish their education to marketable levels. Let's help them find efficiencies and get there in the same duration. We shouldn't compel companies to preserve a hiring pipeline; now should we incrementally upgrade university educations. Better to go to kids in schools & universities and stimulate their creativity, get them using new tools in new ways, finding efficiencies - because that's what today and tomorrow's jobs will be about. Institutions will adopt the good ideas in time.
We have a responsibility to invest in - and invent - ways of bringing people along.
This feels like the centuries-ago transition of peasants from subsistence farmers to economically valuable consumers: thousands of Microserfs, spat out by a geriatric company that lost its ability to leverage their strengths. Their intelligence, their cognitive work product, will be their own again.
Awful for some affected folks; great for others, but SUPER great for everyone who stands to benefit from these talented folks' ejection into the great unknown of "holy shit I need to make money, lemme skate where the puck's going"
Some may even disrupt Microsoft. After all Microsoft can't force their knowledge out of their minds.