bicx

Yes, it is cool

Most of us could never afford a roadster in any form, and just like to see cool stuff on the internet.

It clearly does not look like a smaller Cybertruck though. You're just wrong there.

Not really that crazy. It’s just an ad.

Honestly I’d blend it more. Maybe reduce the contrast a bit and so it’s not the first thing your eye goes to.

In the last couple of weeks, I’ve seen headlines about SF AI safety workers intertwined in a sex cult, a crowdsourced Bay Area list of guys who committed sex crimes, and now this. What’s going on over there?

My team is in the agentic orchestrator phase. I like this software factory pattern in concept, but our biggest challenges in development are acceptance testing of anything UI-related. Mobile app testing in particular is still a huge bottleneck that requires a human. AI models really suck at identifying poor usability and jank, particularly because they only typically process snapshots of the app from an instance in time.

I know there are traditional testing frameworks that can detect jitter and frame drop to a certain level. We could potentially start having agents build that in.

If we had concrete designs and specs on every project, that would also be helpful, but in a fast-moving startup, that gets delegated to the builders. That puts a human back in the loop every time.

Curious to hear what anyone else does to fully adopt a software factory pattern.

I think Google/Meta surveillance just feels like something painless, benign, and invisible. You couldn’t see a reason a huge corporation would really want to target you or put you in danger. With Flock, your local law enforcement has access, and that feels like a much more real threat (warrantless tracking of your real-world activity with the ability to ruin your day/life), not to mention how it’s already been abused to track exes of officers, had be easily hacked in the past, and that AI face recognition matched the wrong people.

The U.S. leadership has a bad habit of starting conflicts that the bulk of the population doesn't want, which leads to large political costs and resulting half-measures. Our current leadership literally ran on "no more wars." Morons.

I wonder if this is a sign of things to come for dirt-cheap model hosting: no servers running old versions, only new versions. Just to keep costs down.

Dead link for me

Gemini is still my top choice within production software for typical data extraction from unstructured data. Gemini Flash Lite feels like a cheat code for speed, and it's really cheap.

Some other Chinese models are also fast and cheap, but a harder sell in a U.S. production environment.

Jesus Christ. This administration has no shame.

It’s an extremely consistent experience, and you can sit in the front seat (something I like personally). With Uber and taxi services, you never know what kind of driver or ride you’re going to get.

You really have to believe your own narrative to do well as a startup founder, even when evidence is initially scant. This likely also has a tendency to slide into self-delusion.

I'm tired of being strung along on these silly narratives. I can't wait for open-weight models to be deployed around the world just so people like Dario will shut up about the mystical levels of power these models have.

They built a comparison harness between the old and the new query, and ran it across thousands to benchmark and ensure valid results. And then I reviewed the PR.

Yes, I’m a senior engineer at a 3-engineer startup, and there isn’t “junior-level” or “senior-level” work here. It’s all just work. Claude allows me to tear through the kind of gruntwork I’ve been doing ad nauseam for the last 15 years.

If my tasks were things like squeezing 3% more efficiency out of an algorithm, that might be different. Although, even then, my PM (!) used Claude to boost the efficiency of one of our more complex Postgres queries by up to 5x, in ways I honestly would not thought of doing. It was quite humbling. A former engineer here used pgMustard on the same query a couple years ago and claimed it was as fast as it could get.

I can’t speak for the kind of work done in the higher echelons of big tech, but for us, there isn’t much that Claude can’t help with.

It was the BEAM process/actor model that fit much better for managing agents, and then there was the out-of-the-box live UI with Phoenix/LiveView that was really appealing. I had started the project in Typescript/Node (because that's my company's primary stack choice), but it hit a plateau in reliably managing multiple independent long-lived agent processes (not really what Node is designed for). I could have used an even more boring tech like Go with more robust process management, but Elixir and Phoenix also came with a lot out of the box. It's no surprise that OpenAI's reference project for agent orchestration (https://github.com/openai/symphony) is also written in Elixir.

We're in an interesting time where my framework/stack choice is now much less dictated by existing engineer expertise and more about fundamental capabilities in the framework and stack themselves.

I ended up building an agent orchestrator in Elixir and Phoenix, not because I love working in Elixir/Phoenix (I do, but I just don't write code by hand anymore), but because the BEAM/OTP capabilities genuinely worked more reliably and elegantly to solve our orchestrator challenges.

I see projects like Hologram potentially showing up as the right tool for the job much more often. The barrier to picking up a new tool/framework/stack is so low these days with agentic development, and it comes down to speed, capability, and reliability.

Ironically, I don't think agents are going to suggest anything like Hologram on their own, so it is still down to human engineers to push it into common use. That might be the biggest barrier to adoption: overcoming obscurity so that LLMs suggest it as a solution.

I guess what we don't know is how many people are on these flights, before or after Trump.

You don’t have to exercise at all though. The far greater majority are people who don’t like exercise at all, and won’t do anything. To have a person do at least some exercise of any form is a big win for their health anytime it happens. That’s what we don’t want to discourage.

You definitely seem to have a much lower exposure level to flagship AI models. I manage fleets of AI agents (and manage engineers who manage fleets of AI agents) all day for my job, and I’m rarely touching code anymore. It’s not perfect, but it is insanely powerful.

I’m having to actively plan for changes to our EPD org because what we need engineers to do today is a lot different than a year ago.

I also wonder if it will develop a negative stigma as a cheap beater truck used in company fleets and such.

Redesigned and rearchitected our company's backend and mobile apps in about 2 months with 1 engineer and 1 PM trained to work with Claude. We used a custom-built multi-agent harness to crank through lots of parallel tasks, which necessitated the API usage.

I wish I only paid $200/mo for Anthropic! Multiply that by 20x.

As a Claude Code user, you almost certainly will. Even using the same OpenAI model with an agent like Codex will likely perform better. An agent can test and iterate on its own solution until it meets the defined success metrics. If you’re working within an existing code base, having preexisting code to demonstrate similar implementations also significantly improves the quality of results, and that’s something an agent can dig into as part of its solution process. I haven’t used ChatGPT in a while, so maybe it’s more sophisticated than it used to be, but I think you’ll see much better results with the latest agent tools.

Which LLM though? Models can still be significantly different in their capabilities.

People here seem a little confused. This is a simulator in the same way Goat Simulator is a simulator. It’s from a collection called “screen toys” and it’s meant to be mindless fun.

The story of literally 95% of tech startups

The captchas are causing me uncontrollable stress