datadrivenangel

It's funny because it's so true

Different flavors of magic require different ritual components and in the name of all that is stable and production worthy, please don't get a necromancer to do your civil construction magic.

Vendor-neutrality helps reduce lock-in, and OpenAI and Anthropic are big enough that the reduction is valuable.

Absolutely not. This is inherently insecure.

And bash is fast! Reminds me of the 230x faster than hadoop blog:

https://adamdrake.com/command-line-tools-can-be-235x-faster-...

Shareholder nuisance lawsuits can happen basically any time the stock goes down... or doesn't go up enough, and often companies will settle instead of the expensive fighting...

If the code is simple, the tests aren't much extra work.

High test coverage doesn't mean your code is good, but it at least reduces the rate at which you accidentally break stuff.

SLAs don't relly get you meaningful money back, they give you a way to get out of long contracts early and switch to a better vendor.

Dirty reads is a classic symptom of scaling poorly. Eventually consistent database writes are fine, but it's a bad look if a user takes an action and then doesn't see the results of their action.

but it's bad enough to be worth not upgrading.

non GAAP. If they were GAAP profitable they either wouldn't be sharing or would be IPOing already.

With better ergonomics around handling failures.

Open weight models are all built on IP theft as well. Also more like 6-12 months behind, maybe 18 but it's hard to say.

LiteLLM's problem isn't really features, it's how bloated all the features are, and specifically how AI maximalist and janky their dev practices are.

if it was less elegant from a function/cost perspective, it would have been replaced a long time ago.

Gattica disagrees.

humanoid robots are decades away, and they are not going to be good or cheap for a long time.

so for an hour flight it costs $5?

Data Science Tasks (Internal) doesn't include time for Astra... same for Database Migration Tasks (Internal)... But does for gpt 5.6 sol.... which is funny.

Same for HealthBench Professional and a few others.

Clearly either OpenAI is very sloppy or GPT-6 Astra is also sloppy.

150k tokens per minute at 1.5k tokens per second means you can have like 3 users concurrently and that's not a lot.

DXF is just a tough format. Get sol to visualize it first and use GIS algorithms on it.

The complaint about not being able to switch between linear and log is valid, which is what I did for making a 3D speed/cost/quality frontier application for a recent meetup talk: https://www.williamangel.net/apps/model_performance.html

Because speed is important, as the reasoning and hardware determine both cost and speed. it's a three dimensional tradeoff.

It's bad accounting to only look at marginal cost and ignore depreciating hardware asset costs.

Yeah this is really funny and annoying. They get better later on in the article, but it is questionable.

The author does not deeply mention that quality/intelligence is a third dimension here in addition to throughput and latency, and the frontier is jagged so quality and intelligence require bespoke benchmarks to evaluate tradeoffs for speed and cost.

The 20 minutes was one of the longest and hardest 20 minutes of my life. The worst.

Did confirm that I have very above average reaction times though.

Firefox is still great!

Notion is blurring the line and trying to get people to build workflows and applications with notion as "the database"...

They should also not list their day rate and triple it.

The problem is that skill at coding is not exactly the same thing as skill at developing and maintaining software, and AI can help there as well, but a swarm of cowboy coder agents will get you to a legacy codebase very very quickly.

And even if the AI is better than most humans, the speed means that you get more defects and issues! If a human developer has a change failure rate of say 10%, (1 in 10 changes causes a defect or issue), and AI is twice as good and only introduces bugs 5% of the time, but submits 10x as many changes, then you go from 1 bug per unit of time to 5 bugs per unit of time, so your velocity is up 10x but your defect rate is up 5x...

Exploding the universe violates my preferences.