The article describes data showing a correlation between Ozempic use and slowed progression of certain brain conditions. The study aimed to determine whether that effect came from Ozempic itself or simply from weight loss. Once researchers controlled for weight loss, the effect disappeared. In other words, correlation, not causation.
That's an important caveat. But effectively it sounds like Ozempic typically results in a better diet, and a better diet typically results in slowed progression.
Having tried a few of these agent frameworks now, ADK-Python has easily been my favorite.
- It’s conceptually simple. An agent is just an object, you assign it tools that are just functions, and agents can call other agents.
- It’s "batteries included". You get a built-in code execution environment for doing math, session management, and web-server mode for debugging with a front-end.
- Optional callbacks provide clean hooks into the magic (for example, anonymizing or de-anonymizing data before and after LLM calls).
- It integrates with any model, supports MCP servers, and easy enough to hack in your existing session management system.
I'm working on a course in agent development and it's the framework I plan to teach with.
I would absolutely take this for a spin if I didn't hate Go so much :)
I've gotten 7 years out of my 2018 iPad Pro and, for my use case of video, browsing, and Procreate, it feels like new. And I believe a big part of that is that the A12X was wildly overpowered when I bought it.
I think someone deciding between an M4 and an M5 today should consider its value 5 years down the road, rather than its value today.
Same. Also have a super old iPad Pro, and it still works amazing. I always ponder upgrading, knowing that I’ve gotten so much use and enjoyment out of it, but then get wrapped around the axle about how the CPU is absurdly overpowered for what I do with it (YouTube, podcasts, music, drawing/note taking, reading). It’s my main device at home, too, so I never feel like I need to upgrade my phone - it’s definitely saved me money in that regard, too. :P
> In the era of Emperor Augustus (27 B.C. to 14 A.D.), a Roman centurion was paid 15,000 sestertii. Given that one gold aureus equaled 1,000 sestertii and given there was eight grams of gold in an aureus, the pay comes to 38.58 ounces of gold
Today, 38.58oz of gold would be a salary of $156K/yr.
If we do the same for silver, it comes out to about 470oz of silver. So $23,500/yr.
If we compare that to a US Army E-8 (say 80k/yr), we can argue that gold has doubled its value relative to labor and silver has dropped to almost a quarter.
I use Markov chains as an example of a "Small Language Model" in teaching LLMs.
My favorite thing about them is that you can use them to demonstrate temperature. The math is basically the same, and it has a similar effect of creating more creativity in the response.
from math import log, exp
from random import choices
# Likilihood of transitioning from of curr_word to next_word
transitions: dict[dict[str, float]] = {...}
def next_word(current_word, temp=1.0):
if current_word not in transitions:
return random.choice(list(transitions.keys()))
probabilities = transitions[current_word]
next_words = list(probabilities.keys())
pvals = list(probabilities.values())
logits = [log(p) for p in pvals]
scaled_logits = [logit/temp for logit in logits]
max_logit = max(scaled_logits)
exps = [exp(s - max_logit) for s in scaled_logits]
sum_exps = sum(exps)
softmax_probs = [exp_val/sum_exps for exp_val in exps]
return choices(next_words, weights=softmax_probs)[0]
def generate_sequence(start_word, length):
sequence = [start_word]
current_word = start_word
for _ in range(length - 1):
current_word = next_word(current_word)
sequence.append(current_word)
return sequence
Some outputs of this when the transitions are trained on a lyrics dataset.
> print(" ".join(generate_sequence("When", 20, temp=0.1)))
When I know that I know that I was a little thing that I know that I don't know that
> print(" ".join(generate_sequence("When", 20, temp=0.5)))
When I don't know you know I can do I see And the river to the light in the time
> print(" ".join(generate_sequence("When", 20, temp=1.0)))
When are melting Little darling, I feel more And if I was very slow (In control) For our troubles And
It's a lot more nonsensical than an LLM, but highlights what the logit manipulation is doing.
I'm surprised by this take. I love YAML for this use case. Easy to write and read by hand, while also being easy to write and read with code in just about every language.
YAML is a serialization format. I like YAML as much as I like base64, that is I don't care about it unless you make me write it by hand, then I care very much.
GitHub Actions have a lot of rules, logic and multiple sublanguages in lots of places (e.g. conditions, shell scripts, etc.) YAML is completely superficial, XML would be an improvement due to less whitespace sensitivity alone.
Sure, easy to read, but quite difficult to /reason/ about in your head, let alone have proper language server/compiler support given the abstraction over provider events and runner state. I have never written a CI pipeline correctly without multiple iterations of pushing updates to the pipeline definition, and I don't think I'm alone on that.
Easy to write and read until it gets about a page or two long. Then you have to figure out stuff like "Oh gee, I'm no nesting layer 18, so that's... The object.... That is.... The array of.... The objects of....."
Plus it has exactly enough convenience-feature-related sharp edges to be risky to hand to a newbie, while wearing the dress of something that should be too bog-simple to have that problem. I, too, enjoy languages that arbitrarily decide the Norwegian TLD is actually a Boolean "false."
This so much this.
Vscode has a very good syntax check github actions yaml so it's not yaml that's the problem.
It's the workflow for developing pipelines that's the problem. If I had something I could run locally - even in a debug dry-run only form that would go a long way to debugging job dependencies, etc. Testing failure cases flow conditional logic in the expected manner etc.
This is why I've become a fan of StrictYAML [0]. Of course it is not supported by many projects, but at least you are given the option to dispense with all the unnecessary features and their associated pitfalls in the context of your own projects.
Most notably it only offers three base types (scalar string, array, object) and moves the work of parsing values to stronger types (such as int8 or boolean) to your codebase where you tend to wrap values parsed from YAML into other types anyway.
Less surprises and headaches, but very niche, unfortunately.
That only matters if you're parsing the same yaml file with different parsers, which GitHub doesn't (and I doubt most people do - it's mostly used for config files)
Can you imagine explaining to someone from the 1800s that we've created a fully generative virtual world experience and the demo was "painting a wall blue"
There's an old documentary where a film crew transported some of those "uncontacted tribe" guys to central London. Rather than being in awe of jet engines or networked internet, the tribesmen guys spent most of their time admiring house construction. "You're telling me there's METAL inside these walls?" I guess we tend to appreciate what we can understand.
The documentary is real. I don't remember a house construction scene but it's been over 10 years since I watched it. It's not an uncontacted tribe, but tribes from Vanuatu and the Solomon Islands.
Reading works of early computer scientists (mathematicians?) like Ada Lovelace or Alan Turing it seems to me that they would be a lot less surprised than some current observers. The idea of artificial mind comes up a lot and they weren't witness to 30 years of slow and uninspiring NLP developments.
It is a little crazy how fast this has changed in the past year. I got VSCode's agent mode to write, run, and read the output of unit tests the other day and boy it's a game changer.
I started listening to the 538 Politics podcast a lifetime ago when they did The Gerrymandering Project. The deep intertwining of history, intentions, and statistics made the narrative compelling. I learned so much about how our democracy worked that I would never have known otherwise.
So, I kept listening and kept learning. It was sometimes difficult, not because of their storytelling skills, but because the news was hard to consume. But the cold numbers helped me manage my emotions with clarity and not disengage.
There's something wonderful about journalism backed by data. The line between news and editorial has long been blurred beyond visibility. 538 was a rare example of a place where smart people could express strong opinions but always had to show the work behind their conclusions.
Yeah, they've been on my podcast subscription list for at least 5 years now, and I'll miss having them around.
I had growing conflicted feelings about the site's overall impact on media, sadly. It felt like, although it was good that they existed as a dedicated organization, they contributed to (or were a symptom of) the overall media landscape's slide into politics coverage as mostly coverage of the horse-race. Sometimes I want to hear what the Scottish teens think a news story means... but more often I want something deeply reported about policy.
I will miss them too. I saw that Galen is already considering starting his own politics pod, but I fear that by immediately jumping into the Substack black hole it will just end up spiraling into the usual engagement-driven slide to the right: https://www.gdpolitics.com/p/my-thoughts-on-the-end-of-fivet...
Imo part of what made 538 work post-blogosphere heyday was exactly that it had backing from legacy media and the funding to continue sharing information with the public without a paywall. As soon as sites go behind a paywall they become a personification of the "media elite" stereotype, where only rich people have the privilege of being informed. But how otherwise to fund not just a cheerful host but a team of data scientists, editors etc in this day and age? Seems like the only interested billionaires do it with strings attached.
