Hacker News: bicx

New comment by bicx in "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"

bicx — Wed, 09 Sep 2026 15:46:04 +0000

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.

New comment by bicx in "GPT-6 Astra"

bicx — Thu, 03 Sep 2026 18:43:39 +0000

Dead link for me

New comment by bicx in "GPT 5.6 Sol is the best "vision" model OpenAI ever released"

bicx — Mon, 17 Aug 2026 14:29:25 +0000

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.

New comment by bicx in "DHS Is Hiring Bounty Hunters to Find and Photograph Deported People's Homes"

bicx — Wed, 12 Aug 2026 01:13:19 +0000

Jesus Christ. This administration has no shame.

New comment by bicx in "Waymo in Dallas"

bicx — Tue, 04 Aug 2026 19:41:26 +0000

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.

New comment by bicx in "The Silicon Valley Founder Meat Grinder"

bicx — Sat, 01 Aug 2026 21:17:59 +0000

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.

New comment by bicx in "Our position on open-weights models"

bicx — Mon, 27 Jul 2026 22:35:35 +0000

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.

New comment by bicx in "What is happening to jobs? Separating AI hype from reality"

bicx — Mon, 27 Jul 2026 16:19:38 +0000

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.

New comment by bicx in "What is happening to jobs? Separating AI hype from reality"

bicx — Sun, 26 Jul 2026 15:25:43 +0000

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.

New comment by bicx in "Hologram Works. Sponsor What Comes Next"

bicx — Thu, 23 Jul 2026 16:11:42 +0000

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.

New comment by bicx in "Hologram Works. Sponsor What Comes Next"

bicx — Wed, 22 Jul 2026 16:32:33 +0000

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.

New comment by bicx in "ICE Flight Monitor Interactive Dashboard"

bicx — Fri, 17 Jul 2026 21:16:00 +0000

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

New comment by bicx in "Weightlifting beats running for blood sugar control, researchers find (2025)"

bicx — Sun, 12 Jul 2026 00:32:10 +0000

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.

New comment by bicx in "Who manages the agents?"

bicx — Sat, 11 Jul 2026 21:22:31 +0000

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.

New comment by bicx in "Why the Slate Truck Only Costs $25K"

bicx — Fri, 26 Jun 2026 03:32:45 +0000

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

New comment by bicx in "Sakana Fugu"

bicx — Wed, 24 Jun 2026 14:28:31 +0000

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.

New comment by bicx in "Sakana Fugu"

bicx — Mon, 22 Jun 2026 14:06:03 +0000

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

New comment by bicx in "Not everyone is using AI for everything"

bicx — Sun, 14 Jun 2026 20:27:34 +0000

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.

New comment by bicx in "No, everyone is not using AI for everything"

bicx — Sun, 14 Jun 2026 16:02:42 +0000

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

New comment by bicx in "Firewood Splitting Simulator"

bicx — Sun, 14 Jun 2026 14:37:31 +0000

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.