Edgars Nemše

Stop hardcoding one model name in your code. Now you can give each request a policy: a small rule for what the call needs It picks the right model for the job, on your own keys This is unhardcoded, our new open source routing for AI models, live today

Steven Bartlett says a few glasses of wine ruined the next 3 days of his life “It's one of those areas where you don't understand the hidden cost until you really give it up for a while. I stopped drinking at 30 years old. I'm now 33. When I was 31, I thought, I'll have a drink again because now I could really A/B test it. I had a year of not drinking, decided to have a drink again” “It ruined three days of my life. I had a couple of glasses of wine, didn't get drunk. It ruined three days of my life because of the domino effect it caused” “I got worse sleep that night, and then because I got worse sleep that night, I ate more poorly the next day because my dopamine system or whatever, the cortisol system was all messed up. I podcasted worse. I didn't go to the gym that day or the day after because I felt really bad. I then slept worse, and I could track all of this on my Whoop”

if you have a toddler, you learn that they generally dislike transitions. like they'll resist going to take a bath, and then they'll also resist getting out of the bath. then you realize that transitions just require energy and adults don't like them either

🦔Microsoft canceled its internal Claude Code licenses this week after token-based billing made the cost untenable, even for a company with effectively infinite cloud resources. Uber's CTO sent an internal memo warning the company burned through its entire 2026 AI budget in just four months. American AI software prices have jumped 20% to 37%, and GitHub (owned by Microsoft) is dropping flat-rate plans for usage-based billing across its products. My Take The AI subsidy era is ending in real time. The same company that put $13 billion into OpenAI and built the Azure infrastructure powering most of Anthropic's compute just looked at the bill from a competitor's coding tool and decided it was not worth paying. That is not a productivity failure on Anthropic's end. Token-based pricing is forcing every enterprise customer to confront the actual cost of running these models at scale, and the number turns out to be far higher than the flat-rate experiments suggested. This ties directly to my Gemini Flash post yesterday. Anthropic, OpenAI, and Google all raised effective prices in the last six months. Enterprises that built workflows assuming AI costs would keep falling are now watching annual budgets evaporate in months. Two outcomes look likely from here. Either enterprises scale back AI usage to fit budgets, which slows the revenue ramp the labs need to justify their valuations ahead of IPOs, or the labs cut prices and absorb the losses, which makes the unit economics worse at exactly the wrong moment. Both paths land in the same place, the numbers stop working, and somebody has to take the writedown. Hedgie🤗

You don't need advice from editors on rejected manuscripts.  My short story “Ender's Game” was rejected by Ben Bova at Analog back when that was the top market for a sci-fi story. Ben gave me feedback. He thought the title should be “Professional Soldier” and he said to “cut it in half.” But I knew he was wrong on both points and submitted it to Jim Baen at Galaxy. He sat on it for a year, and responded to my query with a rejection. There was some kind of explanation, but I don't remember what it was. I concluded at the time that Baen's comments showed that he had barely glanced at the story. So … I got feedback both times, but it was not helpful. I looked at Ben's rejection again. What was it about the story that made him think it should, let alone COULD, be cut in half? Apparently it FELT long. What made it feel long? Now, post-Harry Potter, I would call it the quidditch problem. I had too many battles in which the details became tedious. So I cut two battles entirely, merely reporting the outcomes, and shortened another. In retyping the whole manuscript (pre-word-processor, that was the only way to get a clean manuscript), I added new point-of-view material to the point that I had cut only one page in length. So much for “in half.” But I already knew that my manuscripts did not need cutting — if it wasn't needed, it wouldn't be there in the first place. Even the battles were still there, but instead of showing them, I merely told what happened (so much for the usually asinine advice “show don't tell”), which kept the pace going. Those changes made, I sent it to Ben again. I did not remind him of what he had advised me to do. I merely told him I liked my title, and said, “I have addressed your other concerns,” which was true. I figured he wouldn't remember what his exact words had been. My answer was a check. That revised story was the basis for my winning the Campbell Award for best new writer. Did Ben's feedback help? Yes — but his specific advice was not right, and I knew it. On my next two submissions, Ben hated my endings, and I revised as suggested. The fourth submission he rejected outright, and the fifth, and I thought, Am I a one-story writer? I went back to Ender's Game and tried to analyze why it worked. Then, deliberately imitating myself, I wrote “Mikal's Songbird.” Ben bought it, and it received favorable mentions. I was afraid then that I had consigned myself to writing stories about children in jeopardy. But in fact I was writing character stories rather than idea stories. And THAT was how I built a career, not by self-imitation, and not by following editorial suggestions. I did get wise counsel from David Hartwell on my novel Wyrms, but that was on a book that was already under contract, and it was story feedback, not style. I got wise counsel from Beth Meacham, too, on various books over the years — but again, only on books that were under contract. I also received appallingly stupid advice from the editor of my novel Saints, which temporarily destroyed the book's marketability; after that, I was allowed to go back to my original structure and save the book — now it's one of my best. Editors don't know more than you about your story. They especially don't know why they decide to accept or reject stories. YOU have to know what your story needs to be, and take only advice that you believe in. Your best counselor on a story nobody bought is TIME. Let some time pass and then reread the story. Don't even think about why it Didn't Work. Instead, think about what DOES work, and then write it again, a complete rewrite, keeping nothing from the previous draft. Find the right protagonist and begin at the beginning — the point where the protagonist first gets involved with the events of the story. Be inventive — the failed first draft no longer exists, so you're not bound by any of your earlier decisions. THAT is how you resurrect a good idea you did not succeed with on your first try.

Simple way to see this is wrong: If you view a system as having inputs (like hearing something) and outputs (like saying something) then you can divide system properties by whether or not they affect I/O. Claude's weights somewhere storing "Paris is in France" affect I/O if you ask a question about Paris. The exact mass of the power supply to the GPU rack for that Claude instance doesn't affect I/O. That Claude instance being made out of silicon instead of carbon, or electricity in wires instead of water in pipes, doesn't affect I/O given a fixed algorithm above the wires or pipes. Nothing Claude can internally do will make anything get damp inside, if it's running on electricity. Nothing about "electricity vs water" can affect Claude's output for the same reason. It always answers the same way about France. Nothing Claude can internally compute will let it notice whether it's made of electricity or water flowing through pipes. When someone says "a simulated storm can't get anything wet", they are unwittingly pointing to the difference between the physical layer and the informational/functional layer. Things that the computer physics affect without affecting output; things that affect the output without depending on the exact computer-physics. The material it's made of doesn't affect the output. The output can't see the material because no algorithm can be made to depend on the choice of material. You can always run the same algorithm on different material, so you can't make the algorithm depend on that, so the output can't depend on that. By reflecting on your awareness of your own awareness, the fact of your own consciousness can make you say "I think therefore I am." Among the things you do know about consciousness is that it is, among other things, the cause of you saying those words. You saying those words can only depend on neurons firing or not firing, not on whether the same patterns of cause and effect were built on tiny trained squirrels running memos around your brain. You couldn't notice that part from inside. It would not affect your consciousness. That's why humans had to discover neurobiology with microscopes instead of introspection. Consciousness is in the class of things that can affect your behavior and can't depend on underlying physics, not in the class of direct properties of underlying physics that can't affect your behavior. A simulated rainstorm can't get anything wet. Running on electricity versus water can't change how you say "I think therefore I am." And that's it. QED.

Aqua Voice is now live for iOS. It's a premium voice keyboard for every app on your phone.

95% reliable is ~100% reliable if the hallucinations are uncorrelated across runs/systems/etc. It just means you spend a bit of extra effort on implementing a voting/etc layer and spend more on inference redundantly. This is almost boring.

Slept over at this girl once who had linen sheets and it was the most comfortable sleep I’ve ever had hands down. Zero sweat, superb texture. Well turns out this is like 800$ or so for two sets we’re sticking with ikea.