Hacker News: tomlis

New comment by tomlis in "Windows 9x Subsystem for Linux"

tomlis — Wed, 22 Apr 2026 15:43:59 +0000

amelius was saying that tongue-in-cheek.

New comment by tomlis in "Tesla 'Robotaxi' adds 5 more crashes in Austin in a month – 4x worse than humans"

tomlis — Tue, 17 Feb 2026 21:09:11 +0000

I really don't think that's true. Think Uber vs. Lyft. I know I distinguish between the two even if the experience is usually about the same and people I know where this has come up in conversation generally see Lyft as "off-brand" and a little more skeevy. They only take Lyfts when it's cheaper or quicker than Uber.

I'm probably not the average consumer in this situation but I was in Austin recently and took both Waymo and Robotaxi. I significantly preferred the Waymo experience. It felt far more integrated and... complete? It also felt very safe (it avoided getting into an accident in a circumstance where I certainly would have crashed).

I hope Tesla gets their act together so that the autonomous taxi market can engage in real price discovery instead of "same price as an Uber but you don't have to tip." Surely it's lower than that especially as more and more of these vehicles get onto the road.

Unrelated to driving ability but related to the brand discussion: that graffiti font Tesla uses for Cybertruck and Robotaxi is SO ugly and cringey. That alone gives me a slight aversion.

New comment by tomlis in "Claude Sonnet 4.6"

tomlis — Tue, 17 Feb 2026 20:55:07 +0000

gpt-5.3-codex isn't available via the API yet. Pretty sure they were only testing via API access.

New comment by tomlis in "OpenClaw: When AI Agents Get Full System Access. Security nightmare?"

tomlis — Fri, 06 Feb 2026 01:16:49 +0000

Yeah. One of the patterns I've fallen into looks a bit like this:

1. I have some new task I need/want to do.

2. For whatever reason, it's not something I want to do myself if I can avoid it.

3. Have the agent do it the first few times.

4. After those first few iterations, think about if it's something where the variability in the number of steps needed to complete the task is small enough to just put into a small script or service. If it is, either write the code myself or ask the agent to create draft code based on its own observations of how it did the task those first few times. If it's not, just keep having the agent do it.

5. A good chunk of the time, most of the task has low variability in what it needs to do except for just one portion. In that case, just use deterministic code for all areas of the program except the high variability area.

Probably a better word than "variability" for what I'm talking about but I think you get the idea. Spend a lot of tokens upfront so the tokens used later can be minimized when possible.

EDIT: Formatting.

New comment by tomlis in "Nanobot: Ultra-Lightweight Alternative to OpenClaw"

tomlis — Fri, 06 Feb 2026 01:03:16 +0000

As a rule of thumb, most people who say things like "X is useless and a waste" or "Y is revolutionary and is going to change everything by tomorrow" when the dust hasn't even begun to settle are stupid, overly-excitable, too biased towards negative outlooks, and/or trying to sell you something.

Sometimes they have some good points so you should listen to what they have to say. But that doesn't mean you have to get absorbed into their world view. Just integrate what you see as useful from your current POV and move on.

New comment by tomlis in "Nanobot: Ultra-Lightweight Alternative to OpenClaw"

tomlis — Fri, 06 Feb 2026 00:38:42 +0000

Well, at some point it's up to us to say 'no.' Weekends have not always been a widely accepted ritual[1]. They only became one because of collective action.

Dedicating any and all of your free time to work only becomes a norm if we let it.

[1]: https://www.goodwinrecruiting.com/eight-hour-workdays-and-40...

New comment by tomlis in "OpenClaw: When AI Agents Get Full System Access. Security nightmare?"

tomlis — Fri, 06 Feb 2026 00:25:32 +0000

The deterministic mixed with LLM approach has been great for me so far. I've been getting a lot of the gains the "do it all with AI" people have been preaching but with far fewer pitfalls. It's sometimes not as fluid as what you sometimes see with the full-LLM-agent setups but that's perfectly acceptable to me and I handle those issues on a case-by-case basis.