Hacker News: swingboy

New comment by swingboy in "Grok 4.5"

swingboy — Wed, 08 Jul 2026 23:04:52 +0000

Haven’t heard this one in a while XD

New comment by swingboy in "We're extending access to Fable 5 on all paid plans through July 12"

swingboy — Wed, 08 Jul 2026 11:28:42 +0000

Which 2 or 3 skills?

New comment by swingboy in "Alibaba to ban Claude Code in workplace over alleged backdoor risks, source says"

swingboy — Fri, 03 Jul 2026 11:52:33 +0000

There was a big thread about it here the other day. https://news.ycombinator.com/item?id=48734373

New comment by swingboy in "Global review confirms mRNA vaccines are safe, effective and full of promise "

swingboy — Thu, 02 Jul 2026 02:23:09 +0000

Serious question in good faith: what was the deal with the “calamari” (clots?) the anti-vax crowd kept talking about being found in the veins/arteries of folks who took the Covid vaccine?

New comment by swingboy in "Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5"

swingboy — Wed, 01 Jul 2026 09:04:06 +0000

“Anthropic wants to MAKE A DEAL!”

New comment by swingboy in "Is It Out Yet?"

swingboy — Mon, 29 Jun 2026 23:13:35 +0000

These guesstimate release dates seem…soon. Usually the Polymarket markets are pretty accurate and really accurate when an insider at one of the companies puts a bet.

New comment by swingboy in "Tidal AI Policy"

swingboy — Mon, 29 Jun 2026 14:15:23 +0000

How is this enforceable?

New comment by swingboy in "Knowledge Distillation of Black-Box Large Language Models (2024)"

swingboy — Mon, 29 Jun 2026 10:14:42 +0000

And it’s a paper from Alibaba researchers, the company/lab that Anthropic called out by name.

New comment by swingboy in "HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88"

swingboy — Mon, 29 Jun 2026 09:33:30 +0000

I’ve always assumed any LLM output that was some type of rating or score was bullshit. Unless the LLM writes a Python script to calculate the score (and even then…) then the score it outputs is just the next most likely token, taking into account temperature and what not.

You see a lot of frameworks for things like spec-driven development make use of scoring how good the spec/design/plan is and it’s like, uhhh…

New comment by swingboy in "Turning music into a chore is how I became a musician (2022)"

swingboy — Sun, 28 Jun 2026 13:16:52 +0000

Did he not listen to music made by others when he was isolated in the cabin?

New comment by swingboy in "'Careless People' author claims Meta surveilled her for 12mos to enforce silence"

swingboy — Sat, 27 Jun 2026 23:15:06 +0000

All members of the Epstein class.

New comment by swingboy in "'Careless People' author claims Meta surveilled her for 12mos to enforce silence"

swingboy — Sat, 27 Jun 2026 23:10:05 +0000

Nice try, Barbra.

New comment by swingboy in "U.S. allows Anthropic to release Mythos AI to ‘trusted’ US organizations"

swingboy — Sat, 27 Jun 2026 09:02:43 +0000

How would export controls apply if OpenAI or Anthropic released a model as open weights? Not that they would, but asking out of curiosity.

New comment by swingboy in "U.S. allows Anthropic to release Mythos AI to ‘trusted’ US organizations"

swingboy — Sat, 27 Jun 2026 09:01:20 +0000

Because the American people weren’t outraged enough to push them out.

New comment by swingboy in "U.S. government will decide who gets to use GPT-5.6"

swingboy — Fri, 26 Jun 2026 18:53:00 +0000

Here’s to hoping that Alibaba (and other Chinese labs) have collected some really good distilled data.

New comment by swingboy in "GLM-5.2 is a step change for open agents"

swingboy — Thu, 25 Jun 2026 10:23:28 +0000

My work involves asking LLMs about both Tianenmen Square and what’s going on in Gaza, so I can’t use Chinese or American models!

New comment by swingboy in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

swingboy — Thu, 18 Jun 2026 00:11:48 +0000

I get a 500 when clicking “Explore the Models”

New comment by swingboy in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

swingboy — Wed, 17 Jun 2026 15:53:09 +0000

Anthropic’s best practices still include the use of XML: https://platform.claude.com/docs/en/build-with-claude/prompt...

New comment by swingboy in "Show HN: Vet turned founder, AI lawn diagnosis"

swingboy — Mon, 15 Jun 2026 22:43:27 +0000

*Advice only applies to neighborhoods without an HOA.

New comment by swingboy in "Apple Foundation Models"

swingboy — Mon, 15 Jun 2026 11:09:36 +0000

Does “the best machine for AI use” apply here considering these models are still server-side?