Dima

5.8K posts

Dima banner
Dima

Dima

@UniqueDima

Steak holder, stuff engineer. Building @xmemory_ai. Host of the @SysDesignMeetup. CS generalist, ex. competitive programmer.

Pacific Northwest Katılım Ağustos 2013
1.7K Takip Edilen1.3K Takipçiler
Dima
Dima@UniqueDima·
In a sane ecosystem a competitor to Google Maps reviews on which can’t be silenced emerges overnight, and takes over by a storm. I’m sure @levelsio would take single-digit hours to build a usable one. And our blockchains are good enough these days. For an anonymous solution, cash discounts, etc. And clearly, the customers would benefit. And good restaurants would win as well. I struggle to find a single non-moronic reason to design the regulatory framework this way. And yet here we are. Pathetic Europe.
@levelsio@levelsio

My gf is banned from reviewing places in Europe on Google Maps after she gave one restaurant in Portugal a 1-star review When she reviews inside EU it gets auto rejected, outside EU she can review any place Free speech in Europe has sadly died a long time ago

English
0
0
0
84
Dima
Dima@UniqueDima·
Weird how Elon says he [co-]founded OpenAI because he wanted a counter to Google’s approach to AI: closed, private, for-profit. And as of now the largest benefactor of the ongoing trial is indeed Google — which did soften up since, but all of the original arguments against it by Musk clearly hold true.
English
0
0
1
99
Dima
Dima@UniqueDima·
Speaking of losing faith in your heroes, and speaking of the public and the consumer being largely responsible for the BS happening around us. This: dailycal.org/news/campus/pr… A tragedy if you ask me. And NOT A SINGLE mention of this by Jeff Dean himself, or when you search for his name. You literally have to add Berkeley to get the “original” coverage. It’s not Berkeley who are the jerks here. It’s the people who refuse to speak up about the unacceptability of this very selective law enforcement. And the latter group, of those silently complicit, includes most of the Bay Area. How this is not all over the news is beyond me. How Google is not announcing that from now on it is sending its own security to ensure students can enjoy the event they are coming to enjoy is beyond me. How the provost and the administration of tue university still keep their well-paid positions is beyond me. And this is a rather benign example tbh. There exist far, far worse cases.
English
0
0
0
98
Dima
Dima@UniqueDima·
Here we go — now with a proper tribute to the Science of the Art of AI.
xmemory@xmemory_ai

We’re excited to share that our team at @xmemory_ai has published our main white paper. The core idea is simple: without focus, AI systems try to "remember" everything, and that is where they fail. Schema is the best way to teach them focus. We compared xmemory against major open-source and commercial RAG and hybrid RAG systems, markdown-file memory approaches ("agentic memory"), and memory implementations in customer-facing frontier AI apps. Instead of testing whether systems can recall similar text, we evaluated whether they can store, update, deduplicate, and retrieve facts and relationships reliably. xmemory achieved 97% accuracy, compared with 87% for the strongest competitor. Our core also outperforms the latest frontier models’ one-shot APIs in extraction tasks, showing that the harness matters just as much as model quality. We’ve also open-sourced our measurement datasets and a toolkit to generate new ones synthetically. Huge thanks to the dream team of engineers at xmemory who keep pushing this vision into production. If your company is seeing memory systems fail in real workflows, we’d love to talk.

English
0
0
1
102
Dima
Dima@UniqueDima·
«Помнишь телевизор? Не который плоский, а такая большая коробка в нашем детстве. Вот сколько я себя помню, телевизоры, которые были возле меня, они все были неработающие. Но стоило подойти к одному из них и хорошенечко треснуть его рукой, он начинал что-то показывать. В принципе, это неплохо описывает наш социум.»
Русский
0
0
0
60
Dima
Dima@UniqueDima·
Folks, could you please help me understand how to stay safe with respect to @AnthropicAI's terms of use for Claude Code? I understand that one should not build a for-profit SaaS on top of the Claude Code Agent SDK while using the developer-mode OAuth2-based login. The regular `claude `command line, when run without paying for extra usage and without external API keys, is for personal use only. That part is clear. On the other hand, I can absolutely build my own tooling that runs `claude -p ...` on my own codebase to help me develop and harden it. So where exactly is the boundary? My intention is to stay well within the limits of the Claude Code private plan. I just want to have multiple prompts analyze my own and my team’s code from various angles, so I can get second, third, and fourth opinions from different perspectives: architect, product designer, reviewer, and so on. My harness will definitely monitor the limits carefully and stop before getting close to them. For the most part, I’ll also be monitoring my agents. That said, I do plan to give them longer-running tasks before going to bed, with the hope of waking up to a ready-to-review pull request. Is this comfortably within what is allowed? I’m asking because I’m always very cautious when it comes to trusting my professional and personal well-being to a third party that has control over access. If Anthropic asks me to stop, I’ll stop. If Anthropic asks me to pay for API usage, I’ll do a cost-benefit analysis and make an informed decision. What I want to avoid is the Damocles’ sword of potentially waking up to a restricted Anthropic account because of some misunderstanding. My goal is to remain solidly on the safe side, with enough context and reasoning to clearly explain my case if Anthropic’s internal guardrails are ever triggered by something I’m doing to my own code with Claude’s help. What's the right frame of mind here?
English
1
0
0
76
Dima
Dima@UniqueDima·
@gopikannappan Not true for most high tax countries, with the US being a notable exception — which does indeed tax its citizens overseas.
English
0
0
0
13
Gopi Kannappan
Gopi Kannappan@gopikannappan·
@UniqueDima Most countries tax on residency, not where company is. Moving to Istanbul doesn't help if you're still a citizen of a high tax country.
English
1
0
0
27
Dima
Dima@UniqueDima·
The devil might be in the details, what qualifies for foreign income? If someone co-founds a company and moves to Istanbul, to then draw $1 annual salary and have their company acquired for $XXM in a few years — is it zero tax because it’s cap gain? Because if no, if this is another “no sweat equity” BS play, you’re not attracting talent — you’re attracting old money, or perhaps the children and grandchildren of old money. While who you truly want to attract is young entrepreneurs! I’m still waiting for a country that would say that any blockchain-derived income is taxed at some $10K cap annually. This way we’d be cooking with gas. (My secret dream is that first such country could be Japan in a few years. But, realistically — not very likely.)
The Wandering Investor@wander_investor

HUGE Forget Dubai Panama Paraguay Singapore Hong Kong. “Persons who have not been tax residents of Türkiye for the past three years and who choose to relocate to the country will pay no Turkish tax on their foreign-source income and capital gains for a period of 20 years.” Territorial taxation in a REAL country

English
1
0
0
117
Dima
Dima@UniqueDima·
The P in harness stands for predictability, the D in harness stands for determinism.
English
0
0
0
120
Dima
Dima@UniqueDima·
Thought of the day. In the age of AI, it's the LLM tokens that are expensive. Compute, as in EC2 or ECS or Hetzner, is merely collateral damage. Nobody cares about those costs as long as the LLM tokens are burned with high utility. AI did to compute what compute did to storage. Which also means there's tons of money to be made in compute in the years to come — much like there's tons of money to be made in storage as of the past 5+ years. My bet is the consistency and durability is what will sell well. Both with storage, as of a few years already. And with compute, which is starting about now, since compute becomes the fungible auxiliary unit next to LLM tokens utilized at scale.
English
0
0
0
59
Dima
Dima@UniqueDima·
Been digging deeper into Claude Code leak lately, and a few things are becoming clearer. First, it doesn’t actually use a vector database. That confirms my earlier intuition, and honestly makes me feel better about still paying for Cursor. In practice, Opus via Cursor often feels faster and more responsive anyway. There’s now a Rust port/fork of Claude Code floating around, though — I’d expect that direction to eventually introduce some kind of retrieval or vector layer. Second, Claude Code really isn’t designed around persistent external memory. It’s basically the model’s context window plus whatever lives in-repo (Markdown, notes, etc.). Even its “self-notes” just eat into context. That feels like a strange design choice, especially given how aggressively it uses sub-agents. You’d think it would evolve lightweight internal rules or mini-linters over time — but not really. Third, philosophically, it’s not very “model-first.” In fact, it’s the opposite. Claude Code wraps the model in a heavy harness with lots of guardrails and restricted autonomy — which is ironic, given Anthropic builds some of the safest models out there. Compare that to OpenCode — which basically trusts the model and lets it operate more freely. If you assume a properly sandboxed environment, you could even argue that approach is safer long-term. Less rigid scaffolding, more adaptive behavior. It raises a bigger question: where is all of this heading? Do we end up with every major company building its own agentic coding framework? Or do we converge toward full-blown “agentic operating systems” for development — the Linux / FreeBSD / Windows / macOS equivalents of AI-native coding environments? Personally, I’m still leaning toward curated, manually reviewed extensions layered on top of these systems — scoped per repo or per org. Not fully open (at least for now), but composable and controlled. Either way — this space is getting interesting fast.
English
0
1
1
198
Dima
Dima@UniqueDima·
@prasincs Sadly, yes. He is a good writer though.
English
0
0
1
16
Dima
Dima@UniqueDima·
So good. Also not very true, as least according to Claude: claude.ai/share/03a88e52… I’m starting to comprehend how many factoids these days are blatantly false. And how easy it was and remains to construct false narratives.
Jaynit@jaynitx

In the 1920s, a Stanford psychologist tracked genius children for 50 years. Malcolm Gladwell breaks down what he discovered: Rich families → successful. Poor families → failures. Not average. Failures. Genius-level IQs that produced nothing. He spent 60 minutes at Microsoft explaining why we're wrong about success: The psychologist was named Terman. He gave IQ tests to 250,000 California schoolchildren. He identified the top 0.1%. Kids with IQs of 140 and above. His hypothesis: these children would become the leaders of academia, industry, and politics. He tracked them. And tracked them. For decades. The results split into three groups. The top 15% achieved real prominence. The middle group had average, moderately successful professional lives. And the bottom group? By any measure, failures. The difference wasn't personality. Wasn't habits. Wasn't work ethic. It was simple: the successful geniuses came from wealthy households. The failures came from poor families. Poverty is such a powerful constraint that it can reduce a one-in-a-billion brain to a lifetime of worse than mediocrity. There's a concept called "capitalization rate." It asks a simple question: what percentage of people who are capable of doing something actually end up doing that thing? In inner city Memphis, only 1 in 6 kids with athletic scholarships actually go to college. If our capitalization rate for sports in the inner city is 16%, imagine how low it must be for everything else. Here's something stranger. Gladwell read the birth dates of the 2007 Czech Junior Hockey Team: January 3rd. January 3rd. January 12th. February 8th. February 10th. February 17th. February 20th. February 24th. March 5th. March 10th. March 26th... 11 of the 20 players were born in January, February, or March. This isn't unique to the Czechs. Every elite hockey team in the world shows the same pattern. Every elite soccer team too. Why? The eligibility cutoff for youth leagues is January 1st. When you're 10 years old, a kid born in January has 10 months of maturity on a kid born in October. That's 3 or 4 inches of height. The difference between clumsy and coordinated. So we look at a group of 10 year olds, pick the "best" ones, give them special coaching, extra practice, more games. We think we're identifying talent. We're just identifying the oldest. Then we give the oldest more opportunities, and 10 years later they really are the best. Self-fulfilling prophecy. The capitalization rate for hockey talent born in the second half of the year? Close to zero. We're leaving half of all potential hockey players on the table because of an arbitrary date on a calendar. Kids born in the youngest cohort of their school class are 11% less likely to go to college. 11% of human potential squandered because we organize elementary school without reference to biological maturity. Now here's the part about math. Asian kids dramatically outperform Western kids in mathematics. The gap is enormous and consistent across decades of testing. Some people say it's genetic. It's not. It's attitudinal. When Asian kids face a math problem, they believe effort will solve it. When Western kids face a math problem, they believe the answer depends on innate ability they either have or don't. Here's the proof. The international math tests include a 120-question survey. It asks about study habits, parental support, attitudes. It's so long most kids don't finish it. A researcher named Erling Boe decided to rank countries by what percentage of survey questions their kids completed. Then he compared it to the ranking of countries by math performance. The correlation was 0.98. In the history of social science, there has never been a correlation that high. If you want to know how good a country is at math, you don't need to ask any math questions. Just make kids sit down and focus on a task for an extended period of time. If they can do it, they're good at math. Why do Asian cultures have this attitude? Gladwell's theory: rice farming. His European ancestors in medieval England worked about 1,000 hours a year. Dawn to noon, five days a week. Winters off. Lots of holidays. A peasant in South China or Japan in the same period worked 3,000 hours a year. Rice farming isn't just harder than wheat farming. It's a completely different relationship with work. There's a Chinese proverb: "A man who works dawn to dusk 360 days a year will not go hungry." His English ancestors would have said: "A man who works 175 days a year, dawn to 11, may or may not be hungry." If your culture does that for a thousand years, it becomes part of your makeup. When your kids sit down to face a calculus problem, that legacy of persistence translates perfectly. Now consider distance running. In Kenya, there are roughly a million schoolboys between 10 and 17 running 10 to 12 miles a day. In the United States, that number is probably 5,000. Our capitalization rate for distance running is less than 1%. Kenya's is probably 95%. The difference isn't genetic. The difference is what the culture values and where it spends its attention. Here's the most fascinating finding. 30% of American entrepreneurs have been diagnosed with a profound learning disability. Richard Branson is dyslexic. Charles Schwab is dyslexic. John Chambers can barely read his own email. This isn't coincidence. Their entrepreneurialism is a direct function of their disability. How do you succeed if you can't read or write from early childhood? You learn to delegate. You become a great oral communicator. You become a problem solver because your entire life is one big problem. You learn to lead. 80% of dyslexic entrepreneurs were captain of a high school sports team. Versus 30% of non-dyslexic entrepreneurs. By the time they enter the real world, they've spent their whole life practicing the four skills at the core of entrepreneurial success: delegation, oral communication, problem solving, and leadership. Ask them what role dyslexia played in their success and they don't say it was an obstacle. They say it's the reason they succeeded. A disadvantage that became an advantage. Here's what Gladwell wants you to understand: When we see differences in success, our default explanation is differences in ability. We forget how much poverty, stupidity, and attitude constrain what people can become. We refuse to admit that our own arbitrary rules are leaving talent on the table. We cling to naive beliefs that our meritocracies are fair. The capitalization argument is liberating. It says you don't look at a struggling group and conclude they're incapable. It says problems that look genetic or innate are often just failures of exploitation. It says we can make a profound difference in how well people turn out. If we choose to pay attention. This 60 minute Microsoft talk will teach you more about success than every self-help book you've ever read combined. Bookmark this & give it an hour today, no matter what.

English
1
0
0
116
Dima
Dima@UniqueDima·
So I implemented a fairly large end-to-end UI harness test using Playwright over the past several days. Even got yet another compliment from the CEO that I’m indeed a weird engineer. Which is fair — most engineers can’t be made to write UI tests, and I literally volunteered to build one. Ask forgiveness, not permission. My take was and still is: if you actually care about data isolation across user accounts and system boundaries, end-to-end tests are the best tool we have. Here comes the punchline though. Playwright is enormously good in the age of AI. So good that I’m starting to think instrumented Chromium may be one of the most overlooked security risks. Take online banking or brokerage accounts. Leaking a password is not that scary (sic!), because: - there’s two-factor - a new device or location triggers extra checks - even with access, moving funds to new accounts requires more verification Now imagine the attacker acting on your behalf from your own browser. Your own headless browser. Which most humans have no idea can exist. Headless browsers can open your email, grab the 2FA code, complete the login, and delete that email. And no alarm will ring. Because from the system’s perspective, this is your device. Your browser. Your session. We don’t use CAPTCHAs for bank logins, after all. And you won’t notice anything. Until it’s way too late. So, three thoughts. First: I’m scared. Not so much for myself — my personal paranoia (separate browsers, isolated cookies, etc.) probably protects me from most unsophisticated attacks. But I am scared for the industry. Once this kind of attack becomes widespread, it’s going to be a disaster. Second: I’m annoyed. Because this is exactly the kind of problem the Web3 folks solved at the protocol level a decade ago. Air-gapped device. QR code. Explicit confirmation. Signed response. You see exactly what you approve. Why aren’t we doing this for GitHub commits, pull requests, AWS production changes — anything high impact? No idea. Guess we’ll learn the hard way. The industry has framed the Web3 crowd as a bunch of unsophisticated enthusiasts, unwisely dismissing all the great things built there. And third: the upside. Security in the age of AI is going to become a huge deal, very quickly. And that is actually a good thing! Because this is one of the few areas where first-principles thinking really matters. Security is always an arms race, and the ability to reason clearly about systems will be in very high demand. As for me — with all due disrespect to things like Kubernetes and Terraform — I can kind of see where this is going. Less writing code. More defining invariants, reviewing (semi-AI-generated) rules, and building harnesses that ensure no higher-order policy can be violated by any lower-level implementation. That seems like a good place to invest the time, energy, and passion of hardcore geeks like yours truly.
English
0
0
3
81
Dima
Dima@UniqueDima·
@garrytan Why markdown though?
English
0
0
0
89
Garry Tan
Garry Tan@garrytan·
If your memory dies when your harness dies, you built the harness too thick. Memory is markdown. Skills are markdown. Brain is a git repo. The harness is a thin conductor — it reads the files, it doesn't own them.
Harrison Chase@hwchase17

x.com/i/article/2042…

English
74
199
2.2K
448K
Dima retweetledi
Zynx
Zynx@ZynxBTC·
The UK has a far flatter income distribution than the Communist Soviet Union. The UK take home minimum wage for working a full time job (40-hours) is now £22,555. At £100k salary, the take home is £68,558. That is a net income ratio of 3.04:1 We are now at the point where the wage compression and taxes in the UK means that the difference between minimum wage and a top 5% salary is a net income difference of only ~3x. In the USSR using the same comparison, this figure never fell below 5:1 It's actually even worse in reality because the person earning £100k in the UK often has student loans. Britain is nominally capitalist but functionally communist. China is nominally communist but functionally capitalist. Funny how that works.
English
245
1.4K
9.7K
925.9K