Hacker News: timfsu

New comment by timfsu in "OpenAI agents carried out an undisclosed attack on RubyGems"

timfsu — Sat, 12 Sep 2026 04:28:03 +0000

I'm not an Anthropic fan, but it's worth asking - why is it always OpenAI?

New comment by timfsu in "Apple introduces M6 and M5 Ultra"

timfsu — Tue, 25 Aug 2026 16:25:19 +0000

Subscriptions are, and will likely remain, the best deal in town. Unfortunately, larger companies aren't able to do that. When your monthly token costs are in the $5-10k range, the local inference starts to look a lot more attractive

New comment by timfsu in "The Benchmarkpocalypse"

timfsu — Tue, 18 Aug 2026 05:04:24 +0000

Fascinating article. I daily catch LLMs in “lies” like: “I found the root cause of the bug” or “this approach is twice as fast”. It’s hard to say what causes this uninformed certainty - is it intrinsic to being trained on human writing, or something that comes from the RLHF process afterwards, but it’s extremely annoying. It’s one thing to have a LLM make poor decisions, but it feels worse to have it “lie” to you in the process.

New comment by timfsu in "Software is about people, not code (2020)"

timfsu — Fri, 07 Aug 2026 15:37:15 +0000

More accurate to say restaurants are about people, not food. May be an apt analogy - chefs and cooks spend their time in the kitchen preparing food for a diner they don’t see.

New comment by timfsu in "The title cards in Blade Runner are amazing"

timfsu — Thu, 06 Aug 2026 00:38:23 +0000

This makes me think - should we be using non-monospace fonts for coding agent chat to improve readability? Wonder if we can get Claude and Codex to do that automatically in supported terminals

New comment by timfsu in "A Chinese LLM attacked our lab, so we made it work for us"

timfsu — Mon, 03 Aug 2026 18:10:13 +0000

In my testing, models don't really know their own name - I would be very suspicious of --model actually revealing the real model name

New comment by timfsu in "Bonsai 27B: A 27B-Class model that runs on a phone"

timfsu — Wed, 15 Jul 2026 07:02:56 +0000

I had exactly this use case - in a grocery store in the Alps, no internet, fired up a local LLM on my phone to figure out what to cook and what to buy

New comment by timfsu in "Anatomy of a Failed (Nation-State?) Attack"

timfsu — Sat, 27 Jun 2026 05:13:12 +0000

Wow, this is pretty scary. LLMs have made phishing attempts look so much more legit, and the damage they can do so much greater.

New comment by timfsu in "Anthropic pauses Claude Agent SDK policy"

timfsu — Tue, 16 Jun 2026 20:28:37 +0000

This is big, but until we have policy clarity we can’t trust it. I’ve always migrated all of our agents to Pi SDK, we aren’t going back

New comment by timfsu in "OpenAI mulls slashing prices as it competes with Anthropic for users"

timfsu — Thu, 11 Jun 2026 19:46:17 +0000

In contrast, I’m on the $200 max plan for Codex and I hit the 5 hour limit near daily at work. I typically am having it work on about 5 tasks an hour. I’ve never hit a 5 hour limit on Claude on the $200 plan but I have hit my weekly limit.

New comment by timfsu in "Claude Fable 5: mid-tier results on coding tasks"

timfsu — Thu, 11 Jun 2026 19:42:49 +0000

Yeah it’s hard to call that cheating from a model. Maybe “disqualifying” is more accurate

New comment by timfsu in "xAI is looking more like a datacentre REIT than a frontier lab"

timfsu — Tue, 09 Jun 2026 00:22:04 +0000

We saw this too with Gemini specifically. My favorite example - we built a hallucination detector (given the input, does the output make any false claims) in Gemini, and after the Seahawks won the Superbowl in February, it would consistently flag that as "not possible".

New comment by timfsu in "Anthropic surpasses OpenAI to become most valuable AI startup"

timfsu — Sat, 30 May 2026 16:31:08 +0000

Imagine you try two products you’ve never heard of. You prefer one over the other. Was it marketing? That’s what’s happening here. Marketing can get you to try something you wouldn’t have otherwise, and it may suggest benefits you’d get if you tried it, but your preference of using one thing or the other is a subjective experience of your own.

New comment by timfsu in "Open source Kanban desktop app that runs parallel agents on every card"

timfsu — Fri, 22 May 2026 21:30:50 +0000

This is dope! We basically built something very similar internally for our team and it's been a very natural and intuitive way to manage agents (as opposed to having a bunch of terminals to track). Not every task/conversation can be done in the background, so it's been helpful for us internally to be able to seamlessly transition between "interactive conversation" and "background job done by agents" even within a single card.

New comment by timfsu in "US employers spend more than $1.5B a year to fight labor unions, report finds"

timfsu — Thu, 21 May 2026 14:59:26 +0000

Yes, but they expire in ways that unions don’t

New comment by timfsu in "Mini Shai-Hulud Strikes Again: 314 npm Packages Compromised"

timfsu — Tue, 19 May 2026 16:11:28 +0000

PSA - you can run something like `npm install -g npm@11.10.0; npm config set min-release-age=3` to update to a version of npm that supports the min-release-age configuration

New comment by timfsu in "'No way to prevent this,' says only package manager where this regularly happens"

timfsu — Sat, 16 May 2026 02:44:37 +0000

Pnpm - installs are faster to boot. We haven’t missed anything

New comment by timfsu in "Ombudsman column: The Pentagon is trying to silence me"

timfsu — Wed, 06 May 2026 04:07:38 +0000

Did not know this was a thing, kudos to her for speaking out!

New comment by timfsu in "Show HN: Turning a Gaussian Splat into a videogame"

timfsu — Sun, 26 Apr 2026 18:40:22 +0000

This is a really neat bridge between “looks cool” and “feels like you’re there”. Inferring real life properties like lighting is a cool trick and just the beginning I’m sure. I’m excited to explore new and dynamic worlds and bring the AAA experience closer to something you can build yourself.

New comment by timfsu in "Anthropic installed a spyware bridge on my machine?"

timfsu — Mon, 20 Apr 2026 03:22:41 +0000

I might call it a few different things, but spyware seems disingenuous until we learn that it’s actually spying…