HNHacker News
TopNewBestAskShowJobs

mediaman

6,586 karma · joined April 20, 2009

submissionscomments
mediaman··on Ask HN: How to boost Gemini transcription accuracy for company names?
We do this simply by injecting a company-defined list of proper names/terms into the prompt, within <special_terms>, and telling it to use that information to assist with spelling. It works pretty well.
mediaman··on Claude Memory
He is telling you how it mechanically works. Your comment about it “understanding what that means” because it is an NLP seems bizarre, but maybe you mean it in some other way.

Are you proposing that the attention input context is gone, or that the attention mechanism’s context cost is computationally negated in some way, simply because the system processes natural language? Having the attention mechanism selectively isolate context on command would be an important technical discovery.

mediaman··on Replacing a $3000/mo Heroku bill with a $55/mo server
Bread is a great example! You can buy a loaf for $3-4. It is not a 50x markup. Like growing your own veggies, baking bread is for fun, not for economics.

But the cloud is different. None of the financial scale benefits are passed on to you. You save serious money running it in-house. The arguments around scale have no validity for the vast, vast majority of use cases.

Vercel isn't selling bread: they're selling a fancy steak dinner, and yes, you can make steak at home for much less, and if you eat fancy steak dinners at fancy restaurants every night you're going to go broke.

So the key is to understand whether your vendors are selling you bread, or a fancy steak dinner, and to not make the mistake of getting the two confused.

mediaman··on Production RAG: what I learned from processing 5M+ documents
The point about synthetic query generation is good. We found users had very poor queries, so we initially had the LLM generate synthetic queries. But then we found that the results could vary widely based on the specific synthetic query it generated, so we had it create three variants (all in one LLM call, so that you can prompt it to generate a wide variety, instead of getting three very similar ones back), do parallel search, and then use reciprocal rank fusion to combine the list into a set of broadly strong performers. For the searches we use hybrid dense + sparse bm25, since dense doesn't work well for technical words.

This, combined with a subsequent reranker, basically eliminated any of our issues on search.

mediaman··on DeepSeek OCR
I have a lot of success asking models such as Gemini to OCR the text, and then to describe any images on the document, including charts. I have it format the sections with XML-ish tags. This also works for tables.
mediaman··on Claude Skills
RL works great on verifiable domains like math, and to some significant extent coding.

Coding is an interesting example because as we change levels of abstraction from the syntax of a specific function to, say, the architecture of a software system, the ability to measure verifiable correctness declines. As a result, RL-tuned LLMs are better at creating syntactically correct functions but struggle as the abstraction layer increases.

In other fields, it is very difficult to verify correctness. What is good art? Here, LLMs and their ilk can still produce good output, but it becomes hard to produce "superhuman" output, because in nonverifiable domains their capability is dependent on mimicry; it is RL that gives the AI the ability to perform at superhuman levels. With RL, rather than merely fitting its parameters to a set of extant data it can follow the scent of a ground truth signal of excellence. No scent, no outperformance.

mediaman··on Claude Skills
It's a false dichotomy. LLMs are already being trained with RL to have goal directedness.

He is right that non-RL'd LLMs are just mimicry, but the field already moved beyond that.

mediaman··on DoorDash and Waymo launch autonomous delivery service in Phoenix
We're going in the opposite direction.

High minimum wages are making it nearly impossible to run small restaurants. We're seeing restaurant apocalypse happening in places like Seattle and Denver, because high wages result in high prices which causes lower customer volume which causes higher fixed costs per unit, which causes a death spiral. Denver, for example, has 30% fewer restaurants now, because it's so hard to run one profitably.

Lots of little tasty restaurants and high wages for service staff are basically incompatible. Many people in the city don't realize this and advocate for both.

Of course, high wages are desirable if they can be accomplished without tradeoffs, but the tradeoffs are there.

High minimum wages favor high-volume, fast service chain restaurants that are more labor efficient.

Perhaps eventually automation will relax this tradeoff, but I would expect automation to primarily benefit corporate restaurant chains over small local eateries, unless the automation is so general that any restaurant can start using it without technical expertise or R&D.

mediaman··on You are the scariest monster in the woods
That's already happening. It started happening when they incorporated reinforcement learning into the training process.

It's been some time since LLMs were purely stochastic average-token predictors; their later RL fine tuning stages make them quite goal-directed, and this is what has given some big leaps in verifiable domains like math and programming. It doesn't work that well with nonverifiable domains, though, since verifiability is what gives us the reward function.

mediaman··on You are the scariest monster in the woods
We don't need fossil records. We have a clear chain of evolved brain structures in today's living mammals. You'd have to invent some fantastical tale of how God is trying to trick us by putting such clearly connected brain structures in a series of animals that DNA provides clear links for an evolutionary path.

I'm sympathetic to the idea that God started the whole shebang (that is, the universe), because it's rather difficult to disprove, but looking at the biological weight of evidence that brain structures evolved over many different species and arguing that something magical happened with homo sapiens specifically is not an easy argument to make for someone with any faith in reason.

mediaman··on You are the scariest monster in the woods
In Context Learning (ICL) is already a rapidly advancing area. You do not need to modify their weights for LLMs to persist state.

The human brain is not that different. Our long-term memories are stored separately from our executive function (prefrontal cortex), and specialist brain functions such as the hippocampus serve to route, store, and retrieve those long term memories to support executive function. Much of the PFC can only retain working memory briefly without intermediate memory systems to support it.

If you squint a bit, the structure starts looking like it has some similarities to what's being engineered now in LLM systems.

Focusing on whether the model's weights change is myopic. The question is: does the system learn and adapt? And ICL is showing us that it can; these are not the stateless systems of two years ago, nor is it the simplistic approach of "feeding old context back to it."

mediaman··on The Sveriges Riksbank Prize in Economic Sciences in Memory of Alfred Nobel 2025
This is terribly confused.

Economics is the study of scarcity. Scarcity comes in many forms: land, attention, materials, time. (It is not the study of money, which is a common belief of those who have not thought about what money is. Money is merely a fungible token claim on resources, not the resource itself.)

You could also believe that the study of physics is just the study of business, because businessmen operate in a world governed by physics.

mediaman··on ICE Wants to Build Out a 24/7 Social Media Surveillance Team
Yes, every gigantic new secret police force answerable only to the executive is created to "catch criminals" or "deport immigrants" or do whatever else people will accept, until said police force's mandate is morphed as needed. That is why so many 2A defenders are (rightly) skeptical of large domestic police forces answerable to the executive branch, which is what ICE is; it's also why so many defenders have been skeptical of the FBI, ATF, and so on. The only people who think the mandate won't adjust as needed are, to be blunt, trusting patsies, which is not what 2A defenders have historically been.

The creators and defenders of the second amendment were and are smart people. They were skeptical of highly concentrated power, which is why we have a federalist system; they were also highly skeptical of large concentrations of militarized police power, which is why our police in general are run by states and municipalities. It is really quite difficult to reconcile support of a massive ICE apparatus with any sort of comprehension of the political philosophy of the US constitution.

mediaman··on ICE Wants to Build Out a 24/7 Social Media Surveillance Team
The Federalist papers, Thomas Jefferson, and the Supreme Court as recently as 2008 have all identified the right to bear arms as a mechanism for protection against a tyrannical state. It's surprising as a 2A supporter that you seem unaware of why the amendment exists.

Is that true, or is there something more here?

mediaman··on Anti-aging breakthrough: Stem cells reverse signs of aging in monkeys
Consider looking at social media less and reading more history. The idea that people are recently celebrating cruelty, but did not earlier, is charmingly nostalgic but not exactly historical.
mediaman··on Anti-aging breakthrough: Stem cells reverse signs of aging in monkeys
That understanding of what science is, in its de facto form of practice to date, is remarkably ungrounded from the history of science.
mediaman··on Unix philosophy and filesystem access makes Claude Code amazing
The purpose is not so much Claude Code, but that LLMs running semi-autonomously in a shell environment with access to Unix tools are powerful in a way that a web chatbot is not. Replace Claude Code with some other TUI such as opencode and, modulo some of the specifics of CC's implementation, the truth still stands.
mediaman··on Unix philosophy and filesystem access makes Claude Code amazing
We should have a finish hook that, when the AI decides it's run, runs the hook, and gives it to the LLM, and it can decide whether the problem is still there.

Students don't get to choose whether to take the test, so why do we give AI the choice?

mediaman··on Terence Tao: The role of small organizations in society has shrunk significantly
The reduction of volunteer organizations started long before COVID: "Bowling Alone" was written in 2000, and documents much of the same changes.

The trend has been resistant to any particular link to localized economic ups or downs. Characterizing the 2023-2025 era (at least in the US) as "a time of scarcity" is divorced from any sort of factual reality; there is no quantitative data to support this idea and it seems to mostly be based on social media vibes (hence the oft-commented "vibecession").

One could make a much stronger argument exactly to the opposite: wealthier societies tend to become more individualistic and separated, people choose to live on their own if possible, and in bigger places; large companies have such attractive economics and pay people so much more than small companies do that it is difficult for small organizations to compete for talent.

mediaman··on Tesla is looking to redesign its door handles following trapped-passenger report
The funny thing is that Elon has been very critical of regulation in car design, such as the rules around the side-view mirrors (he wanted to get rid of them and replace with cameras).

But then they find something unregulated and manage to flub it so badly it makes a strong case for regulation.

I'm not sure if Elon was involved in these door handles on the interior, though I do recall he was very involved in the early touch-to-expose exterior handles and insisted they use them despite internal engineering pushback. I think a lot of the bad engineering designs seem to originate from internal engineers getting overruled by Elon.

mediaman··on How big a solar battery do I need to store all my home's electricity?
I don't believe they are UL certified, but Dumfume sells 3.6kwh (300ah-12v) lifepo4 batteries for $320. 15 of those would get you 54kwh for <$5k. Might be tough to be anywhere near that point for UL certified only, though.
mediaman··on Show HN: Haystack – Review pull requests like you wrote them yourself
Meeting notes are useful in two ways, for me:

- I'm reviewing the last meeting of a regular meeting cadence to see what we need to discuss.

- I put it in a lookup (vector store, whatever) so I can do things like "what was the thing customer xyz said they needed to integrate against".

Those are pretty useful. But I don't usually read the whole meeting notes.

I think this is probably more broadly true too. AI can generate far more text than we can process, and text treatises on what an AI was prompted to say is pretty useless. But generating text not with the purpose of presenting it to the user but as a cold store of information that can be paired with good retrieval can be pretty useful.

mediaman··on ChatGPT Developer Mode: Full MCP client access
Simon’s content is not spam. Spam’s primary purpose is commercial conversion rather than communicating information. Your goal seems to be discourage people from writing about, and sharing, their thoughts about technical subjects.

To whatever extent you were to succeed, the rest of us would be worse for it. We need more Simons.

mediaman··on Will Amazon S3 Vectors kill vector databases or save them?
And a topk of 30 also means reranking of any sort is out, except for maybe limited reranking of 30->10, but that seems kind of pointless with today’s LLMs that can handle a bit more context.
mediaman··on The Bitter Lesson Is Misunderstood
This is one reason why verifiable rewards works really well, if it's possible for a given domain. Figuring out how to extract signal and verify it for an RL loop will be very popular for a lot of niche fields.
mediaman··on Amazon has mostly sat out the AI talent war
Interesting theory, but Amazon uses tons of stochastic methods (including deep reinforcement learning) throughout the business, including warehouse inventory management. "Determinism" is not some north star that operations people always adhere to, because the physical world is deeply stochastic and pretending it isn't does not make for a successful operations career.
mediaman··on Web Bot Auth
The website the human sees is the new API.

That's needed because many APIs are either nonexistent or extremely marginal in design and content coverage.

mediaman··on Rendering a game in real time with AI
It's interesting to see software engineers realize that AI can be useful in the hands of competent engineers, but that LLMs tend to produce a mess in the hands of those with little software engineering knowledge. Then they're confused why generative AI asset creation doesn't look that good in the hands of people who have no art training.

I know someone creating a game, and she is using AI in asset creation. But she's also a highly skilled environment technical artist from the industry, and so the use of AI looks totally different than all these demos from non-artists: different types of narrow AI get injected into different little parts of the asset creation pipeline, and the result is a mix of traditional tools (Substance Designer + Painter, Blender, Maya) with AI support in moodboarding, geometry creation and some parts of texture creation. The result is a 2-5x speedup, but instead of looking like slop it looks like a stylistically distinctive, cohesive world with consistent art direction.

The common pattern is that people think AI will automate "other people," because they see its shortcomings in their own field. But because they don't understand the technical skill required in other fields, they assume AI will just "do it." Instead, it seems like AI can be a force multiplier for technically skilled people, but that it begins showing its weakness when asked to take over entire pipelines normally produced by technically skilled people, whether they be engineers or artists.

mediaman··on The Folk Economics of Housing
New supply obviously increases demand because shifting the supply curve to the right (more quantity) reduces the clearing price, which increases demand. That's econ 101. In this classic case, increasing supply both decreases price and increases demand.

But what you're arguing is different: that increasing supply has no effect at all on the clearing price. That would require an unusual demand "curve" that is perfectly flat, i.e., perfectly elastic, where there is infinite demand at a given price and zero demand at just a dollar above that price (or else that infinite demand would have already pushed prices up higher than the pre-existing price).

This clearly doesn't make any sense for the housing market; home buyers are sensitive to price, there is not infinite demand, some people have more or less desire to pay for a house. In fact, perfectly elastic markets essentially don't exist, and very low slope demand curves only exist in some unusual edge cases in markets (such as commodities that are near-perfect substitutes).

mediaman··on The Folk Economics of Housing
Yes, people are going to get squeezed out of the housing market by new arrivals if new housing stock isn't built.

"Squeezing out" is done by a price mechanism: a family that would prefer to stay in Seattle decides to sell, because that new buyer (unable to buy the condo, because it hasn't been built) decides to offer a high enough price to induce the existing family to leave.

That's only done by reducing housing affordability (increasing prices) which is the public policy outcome we're trying to avoid.

It sounds like you agree that new supply is good, I think, because you believe new entrants would otherwise "squeeze out" existing residents and I assume you would agree that this is done by price, and so therefore you would also agree that new housing stock (which decreases the "squeezing") also suppresses price level relative to the alternative fixed stock scenario.

← PreviousPage 6 of 34Next →