Hacker News: gcgbarbosa

New comment by gcgbarbosa in "Litelm: LiteLLM Without the Bloat"

gcgbarbosa — Fri, 11 Sep 2026 20:49:06 +0000

Yeah, but bifrost seems tighter and claims to use way fewer resources

New comment by gcgbarbosa in "Litelm: LiteLLM Without the Bloat"

gcgbarbosa — Fri, 11 Sep 2026 20:25:17 +0000

Actually not. There are so many edge cases. Also these routers are only useful if they have a minimal layer of observability.

Yes, LLMs can do a great job at writing semi-working MVP. Turning it into a usable project still requires a team.

Yeah, maybe for your toy project you can use a LLM written tool.

Also, I am not saying LiteLLM is good either.

New comment by gcgbarbosa in "OpenAI’s Navier-Stokes release included a Lean 4 formal proof"

gcgbarbosa — Thu, 10 Sep 2026 22:00:13 +0000

Maybe, but how many centuries would it take to prove it?

New comment by gcgbarbosa in "AI Mania: From Tulips to Tokens"

gcgbarbosa — Sun, 02 Aug 2026 21:21:14 +0000

How did metaverse revolved around exclusivity or collectibles?

New comment by gcgbarbosa in "Terence Tao's ChatGPT conversation about the Jacobian Conjecture counterexample"

gcgbarbosa — Wed, 22 Jul 2026 18:35:05 +0000

I find it amazing how people can use AI to do things that seem hard but yesterday I could not figure out how to install a package on my system. It kept suggesting dependencies that don't exist, and telling me to use functions that are not in the system. The math does not math...

New comment by gcgbarbosa in "A sociotechnical threat model for AI-driven smart home devices"

gcgbarbosa — Sun, 05 Jul 2026 19:29:37 +0000

It looks well written to me. Research starts with qualitative, then quant...

New comment by gcgbarbosa in "DeepSeek V4 Pro beats GPT-5.5 Pro on precision"

gcgbarbosa — Mon, 08 Jun 2026 07:08:48 +0000

"the intelligence is clearly there"

I wonder if I am using the same models as everyone else. To me, LLMs still give good answers 80% of the time, but 20% it fails in such a miserable way that makes it obvious that the "intelligence" is not there.

New comment by gcgbarbosa in "Can the stockmarket swallow Anthropic, SpaceX and OpenAI?"

gcgbarbosa — Tue, 02 Jun 2026 07:18:27 +0000

Except this is not intelligence

New comment by gcgbarbosa in "Slumber a TUI HTTP Client"

gcgbarbosa — Fri, 22 May 2026 11:19:54 +0000

If it is just an acronym, they can define it as they wish in my opinion.

As long as they defines it first (and they did)

New comment by gcgbarbosa in "Gemini 3.5 Flash"

gcgbarbosa — Tue, 19 May 2026 19:53:44 +0000

funny that when I try the same prompt, gemini generates an image, not an SVG. something is not right.

New comment by gcgbarbosa in "The coming war on car ownership?"

gcgbarbosa — Sun, 25 Jan 2026 09:22:46 +0000

He is the one needing to be diagnosed by a licensed therapist