bicx

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

So, laundered data?

Well, the author specifically mentions the puzzle of how it produces nicotine. Nicotine was first identified and isolated as a chemical in 1828, based on a quick google. So, no one was wondering about nicotine production before then because they didn’t know what it was.

I had been considering getting a Bambu printer precisely for this reason. I had gotten into 3d printing in the reprap era, before selling it off due to lack of space. I don’t really want to get back into that constant calibration and test prints every time the ambient temp or humidity changes a few percentage points. Not to mention the painstaking initial setup. I just want to design and print, not become a 3d printer technician again.

Greg Egan is a legend

Plans like this would be interesting to me if I believed it were possible to get all the necessary parties to agree.

This is really cool and addictive!

Side note: Anthropic has done well at achieving an immediately-recognizable art style.

I think if Walter White were the type to need ChatGPT to figure out meth production, he would have just spent the whole series in that RV, getting nowhere, and accidentally blowing himself up.

Sorry, this is not a good argument. It's sad that some skills are devalued when so many have invested years into them, but it is a net win when more people can create something without having to become an expert. Experts don't deserve to have a moat built around them. I say this as a software engineer with 16yoe who is dealing with the same challenges.

They already have corporate sponsorships from Google, Meta, Nvidia, and other big companies. Anthropic is just joining the list. This is actually good for Blender.

Not sure why this is getting backlash. Just look at https://fund.blender.org. Other corporate sponsors are Google, Meta, Nvidia, Netflix, even Adidas.

This just means more support for a major OSS project.

Going to have a chat with our JSON Engineers to see what our best move might be. It might be worth the adware if we can keep JSONing.

I built an internal company MCP that uses Google Workspace auth and injects a mix of guidance (disguised as tools) on how we would like certain tasks to be accomplished via Claude as well as API-like capabilities for querying internal data and safely deploying small apps internally.

I’d really love to get away from the SSE MCP endpoints we use, as the Claude desktop app can get really finicky about disconnects. I thought about distributing some CLIs with Skills instead. But, MCP can be easily updated with new tools and instructions, and it’s easy to explain how to add to Claude for non-technical people. I can’t imagine trying to make sure everyone in my company had the latest skill and CLI on their machine.

Honey Homes | Early Engineer (Full-Stack / AI) | REMOTE (US) | Full-time

We make homeownership effortless by pairing homeowners with a dedicated handyman and building the software that runs the home.

We're a small team with a product that's growing quickly, and we're backed by top investors. If you like building end-to-end systems with real-world impact, come join us.

Please get in touch at: https://jobs.ashbyhq.com/Honey%20Homes/b3cdd2cd-ffde-41f6-b8...

When they invented cars (and cars became popular and affordable), people did stop walking everywhere. Jogging wasn’t popularized until the 1970s, when we all realized we needed to be intentional with fitness in our car-based society.

No to Palantir in Europe

I recently started riding a motorcycle in the last 2 years. One of my favorite aspects of motorcycles are how easy it is to find a solid 30-year-old bike that still runs well and costs less than $5k. You can still buy parts for it… 30 _years_ later. Nothing else in my life shares that quality. I can continue repairing them and keep them running, which is a fun little hobby.

I really want to like the idea of electric motorcycles, but I have very low confidence that they would be built for the long term. Having to worry about software and security makes me even less excited.

Anthropic is the leading enterprise LLM provider. All they have to do is keep building a best-performing product, charge what they need, and keep costs as far down as possible. If my company knew there were an LLM 1.5x as good as Opus, they would be willing to pay 3x the cost. If it were being sold by Anthropic, they’d be even more likely to pay, since we could easily keep our same tooling.