A biologist lost somewhere in the gap between academic success and economic failure. I like molecular biology, statistics, evolutionary theory, new ideas, and anything that challenges my assumptions.
Github here: https://adamdoescode.github.io/
Submissions
The Latest Computer Vision Model Updates (iNaturalist)
inaturalist.org
2 points·by ImaCake··0 comments
Bespoke open databases would be cheaper and easier to analyse
nature.com
1 points·by ImaCake··1 comments
The world’s species are playing musical chairs: how will it end?
nature.com
3 points·by ImaCake··2 comments
Former grad student has paper retracted after mentor objects
I find it helpful to think of LLMs as reflections. If you can talk like an expert mathematician at the model it will respond like one. While Terrance's first prompt looks trivial I expect a first year Uni student would be hard pressed to provide something that good.
I guess it is kind of the inverse of the "you are an expert mathematician" prompt engineering of gpt3.5. Since no one ever says that to an expert mathematician when they are doing expert math the model immediately reflects that it is not an expert mathematician.
Sorry if my speculation was bad! When I wrote it I meant it as a compliment. Raw LLM output is awful and really needs a human to "translate" the useful content to something worth reading.
It seems too concise to be AI. My (conscious) heuristic for AI writing is how much context is squeezed into a sentence. LLMs seem to be pretty bad at the kind of elegant compression of meaning humans can do when they have done a lot of writing practice.
If I had to guess, I would say this is the human summarised conversation(s) with a bot.
I guess ask the bun people why they translated from zig to rust. I think it was essentially because rust guarantees a set of bugs can't exist so over medium to long term timeframes you end up with less technical debt.
Significantly cheaper than comparable models if you are using openrouter [0]. Just yesterday I spent roughly 13 cents centering some divs using Deepseek in a personal project. It would have been north of $1 to do that with a US frontier model.
You should try out the cheaper models first. I find Deepseek v4 models pretty comparable to sonnet 4.6 but at a fraction of the cost. You might find you just don't need to use the American models at all.
That first map seems to map quite closely to koppen climate zones across the continent. Its hard to say whether the climate is decisive here because climate is a big influencer of urban design. However, its interesting that in Australia its the two Mediterranean climate cities (Perth and Adelaide) which frequently get labelled as worse for tree cover compared to the sub tropical east coast cities.
It's fun and it looks good regardless of whether its 100% correct (It would certainly take me more than 9 hours of work to do better than this). Making these bespoke tools possible for most people is a big deal.
People are not (yet) aware what has been making everyone fat, but ozempic is making it harder to ignore that ultraprocessed foods are the culprit. So hopefully this will change.
In my experience, LLM usage follows an exponential distribution i.e. most people using LLMs are not using many resources, but a very small few are using a massive amount of resources. Most LLM usage is trivial and tiny, most of what I use LLMs for could be done by a local model with a decent web retrieval tool. What some people I know use LLMs for requires massive volumes of tokens. Its that small power user base which I would bet they are targetting.
I think this falls flat for a technical audience because we already know how to do this stuff. But there are a lot of people who don't know how to copy paste, or use reverse image search, or apply a filter to a table. Being able to use plain language to do these things is a game changer for them. Sure, it's inefficient and inelegant but it's an interface that will do for basic technical stuff what the ipad touch screen did for the mouse and keyboard.
I read/listened/sampled a lot this year but a few have reached out into my life and changed me at least a little bit.
- In Defense of Food - Michael Pollan. A brilliant "not diet" book about not eating crap and enjoying chocolate cake with your friends. I followed this up with Ultra Processed People to arm myself with the facts to defend not eating the junk people call food.
- The Dispossesed - Ursula Le Guin: recommended in previous year's HN what did you reads. An absolutely triumph for how it manages to portray a believable anarchist society.
- Adult Children of Alcoholics: useful to the multitude of us who grew up with an alcoholic parent(s). I used this to identify the common patterns I share with others who grew up like me. You are not alone!
- The Invention of Clouds (not finished): I really like the context of "dissenting science" which the author conveys brilliantly. Turns out Dark Academia and Bro Science are not new.
- The Art of Frugal Hedonism: Irreverant although it comes off a little pious. This book has helped me accept that I have enough stuff already.
Can't speak for OP but I largely spend it reading (and web). I bought a kindle recently because I found the ipad/iphone were too distracting to reliably avoid web surfing instead of a book. I view the switch to long form content as a form of information dieting in the same way as a switch to whole foods.
I think a lot of this is because people (and thus LLMs) use verbosity as a signal for effort. It's a very bad signal, especially for software, but its a very popular signal. Most writing is much longer than it needs to be, everything from SEO website recipes, consulting reports, and non-fiction books. Both the author and the readers are often fooled into thinking lots of words are good.
It's probably hard to train that out of an LLM, especially if they see how that verbosity impressess the people making the purchasing decisions.
Github here: https://adamdoescode.github.io/