Hacker News: osigurdson

New comment by osigurdson in "OpenClaw’s memory is unreliable, and you don’t know when it will break"

osigurdson — Sat, 11 Apr 2026 14:42:06 +0000

Can you be more specific about these? For instance can you map "analyzes our current marketing efforts" to precisely what is being fed into the context window. What prompt is used to "find something useful"?

Like many here, I am struggling to see a meaningful delta between OC and CC but fully willing to accept that my skepticism is misplaced. Basically, I am in "trying to care about OC" mode right now.

New comment by osigurdson in "OpenClaw’s memory is unreliable, and you don’t know when it will break"

osigurdson — Sat, 11 Apr 2026 14:14:10 +0000

I'm confused about it as well. I've installed OC locally and also on a VM. I don't get it so far. But then again, I'm not willing to give it all of my passwords which is probably why I'm not seeing much value. It isn't just non-coders that see OC as a game changer however.

New comment by osigurdson in "OpenClaw’s memory is unreliable, and you don’t know when it will break"

osigurdson — Sat, 11 Apr 2026 14:06:34 +0000

Agree. It is like just having one continuous chat session with ChapGPT forever. Of course they do have memory already (at least ChatGPT does). I ended up turning it off however, because it kept bringing irrelevant stuff into the current convo.

New comment by osigurdson in "OpenClaw’s memory is unreliable, and you don’t know when it will break"

osigurdson — Sat, 11 Apr 2026 14:03:09 +0000

Just curious, what is the delta with this and Claude Code / Codex CLI for the SWE work?

New comment by osigurdson in "Lisette a little language inspired by Rust that compiles to Go"

osigurdson — Tue, 07 Apr 2026 16:11:30 +0000

It sounds like you know about this / have researched it. Are you saying that any go function, even func add(x,y int) { return x + y}, is going to have such overhead in all situations? Why wouldn't Go just inline this for instance when it can? It seems like such an obvious optimization.

New comment by osigurdson in "Dropping Cloudflare for Bunny.net"

osigurdson — Tue, 07 Apr 2026 15:21:30 +0000

I didn't downvote it, but I don't think migrating away from Cloudflare workers, R2, D1, etc., isn't going to be that easy. Basically, the build these things from the ground up to work optimally for their infra - even the mental model that you have to use is different. If you only narrowly use one part of it, maybe.

New comment by osigurdson in "Dropping Cloudflare for Bunny.net"

osigurdson — Tue, 07 Apr 2026 15:18:52 +0000

Logically, the only thing CloudFlare would do is lower or eliminate the free usage tier. For instance, if X million operations are currently free, they make X/2 operations free. I don't think they would do that, but if they did, it couldn't possibly be existential to any viable company.

Practically, any metered supplier can put you out of business. It usually doesn't happen because destruction is mutually assured.

+1 for using smaller, more independent companies in any case!

New comment by osigurdson in "Sky – an Elm-inspired language that compiles to Go"

osigurdson — Mon, 06 Apr 2026 23:35:43 +0000

I understand the motivation as I don't really like writing Go code. Interestingly, I don't mind reading it though (as long as the if err != nil isn't too exhausting).

A transpilation step though? I'll accept that in Typescript (barely) but not for any other language really.

New comment by osigurdson in "Lisette a little language inspired by Rust that compiles to Go"

osigurdson — Mon, 06 Apr 2026 15:04:16 +0000

I'm not sure this is 100% correct. I haven't researched it but why would they perform such a check at runtime if it is 1)material and 2) can be done at compile time. However, even if it is, Go is only trying to be medium fast / efficient in the same realm as its garbage collected peers (Java and C#).

If you want to look at Rust peer languages though, I do think the direction the Zig team is heading with 0.16 looks like a good direction to me.

New comment by osigurdson in "Lisette a little language inspired by Rust that compiles to Go"

osigurdson — Sun, 05 Apr 2026 14:55:54 +0000

I'd always liked the Go runtime but the language is pretty clunky imo and I don't think they will ever improve it (because they don't think anything is wrong with it). However, you have to really dislike the language to use a transpiler.

New comment by osigurdson in "Lisette a little language inspired by Rust that compiles to Go"

osigurdson — Sun, 05 Apr 2026 14:49:44 +0000

Go's async story is great, as there is no function coloring at all. That being said, I don't like Go's syntax very much. The runtime is great though.

New comment by osigurdson in "Ubuntu now requires more RAM than Windows 11"

osigurdson — Sun, 05 Apr 2026 14:40:45 +0000

Agree. I'm able to do development, run multiple containerized services (including Postgres, NATS, etc), have 10 browser tabs open, all on an 8 GiB laptop running Arch. I have a desktop with 64GiB as well but realized there is no point using it most of the time.

New comment by osigurdson in "Shooting down ideas is not a skill"

osigurdson — Sun, 05 Apr 2026 02:13:18 +0000

I think what most successful people do is avoid getting in situation where they have to ask for permission to do things. While there may sometimes be legitimate gate keepers that stop you, be careful not to create a gatekeeper out of people that don't care one way or the other. Just go ahead and do it if you can.

New comment by osigurdson in "Embarrassingly simple self-distillation improves code generation"

osigurdson — Sat, 04 Apr 2026 19:54:55 +0000

That is a very interesting thought!

New comment by osigurdson in "Let's be Honest about AI Coding"

osigurdson — Sat, 04 Apr 2026 05:58:41 +0000

Agree. I think it is a little reductive. Regex / free text search can obviously miss things (as can vector stores). Combining both of them is fairly typical (along with a re-ranker, potentially). You are basically trading quality for latency and cost.

New comment by osigurdson in "Wired headphone sales are exploding"

osigurdson — Sat, 14 Mar 2026 14:58:54 +0000

I never understood the appeal of AirPods. To me, it just seemed like an inferior product at a much higher price. You now have to worry about charging them (not to mention charging the case), you have three things that are easy to lose vs one that is hard to lose, and finally, to my taste, they are somehow gross to look at - like hearing aids from the 1950s. The product just seems like a manifestation of complexity for the sake of complexity.

New comment by osigurdson in "Levels of Agentic Engineering"

osigurdson — Tue, 10 Mar 2026 23:17:04 +0000

"Level 8" isn't really a level, it is more like a problem type: language translation. Perhaps it can be extended to something a bit broader but the pre-requisite is you need to have a working reference implementation and high quality test suite.

New comment by osigurdson in "Agents that run while I sleep"

osigurdson — Tue, 10 Mar 2026 22:21:23 +0000

I think the solution has to be end to end tests. Maybe first run by humans, then maybe agents can learn and replicate. I can't see why unit tests really help other than for the LLM to reason about its own code a little more.

New comment by osigurdson in "Agents that run while I sleep"

osigurdson — Tue, 10 Mar 2026 22:18:13 +0000

So more stuff happens with this approach but how do you know what it generates is correct?

New comment by osigurdson in "After outages, Amazon to make senior engineers sign off on AI-assisted changes"

osigurdson — Tue, 10 Mar 2026 22:06:05 +0000

Exactly. This is real world pushback on the "software is solved" narrative from AI labs. Also, most orgs try to copy Amazon for some reason more than big tech firms. "At our org, we disagree and commit" - yeah you made that one up yourself. Anyway, this is going to have a lot of impact in my view.