Hacker News: dgunay

New comment by dgunay in "Ask HN: Are you working 996 hours?"

dgunay — Tue, 04 Aug 2026 20:24:05 +0000

No, but if I got paid overtime I'd absolutely do it (or something more reasonable like 50-60 hrs/week)

New comment by dgunay in "Waymo in Dallas"

dgunay — Tue, 04 Aug 2026 19:47:24 +0000

It sounds too much like "parasite" for me to be comfortable using it. I'm assuming some random person made it up. It's okay to just say "people of/from ", guys.

New comment by dgunay in "RamenHaus"

dgunay — Sat, 01 Aug 2026 23:15:16 +0000

At least where I'm at, you can still go cheaper for pizza and burgers. In-N-Out's combo meals start at about $8. If I want to, I can also get 2 big slices of serviceable pizza for a bit less than $10 in a mom & pop shop, and this is in a city that IMO punches well below its weight when it comes to pizza.

New comment by dgunay in "Golang proposal: container/: generic collection types"

dgunay — Sat, 01 Aug 2026 08:44:42 +0000

It's cool that they're doing this but with iterators and soon in 1.27 generic method parameters, you can already DIY most of this with little effort. I've got iterators at work for nearly everything I could want, small libraries for extra mapping, filtering etc operations, and with agents going back and actually refactoring old code to use them is easier than ever.

New comment by dgunay in "qm – Multiplayer agent harness for work"

dgunay — Sat, 01 Aug 2026 00:49:48 +0000

I have been seeing people use it more who I am fairly confident are not otherwise using AI to write public-facing communications. It's almost like there's a minor movement to try and reclaim it. Either that or it's somehow getting past my AIdar.

New comment by dgunay in "The AI Aesthetic"

dgunay — Fri, 31 Jul 2026 00:40:07 +0000

There's definitely a lot of AI-generated websites, especially for dev tools & SaaS, that love to have dark backgrounds, cool colors (purple especially is making a resurgence it seems), and tons of fancy UI widgets.

New comment by dgunay in "Agent Skill to Force Docs in ASD-STE100 Simplified Technical English"

dgunay — Fri, 31 Jul 2026 00:29:35 +0000

I don't understand the challenges involved super well but I feel like this might be better as a piece of actual code (like a linter) that you can run to have an LLM iteratively de-slop its own writing, rather than forcing it out of distribution and having to contend with all the unreliability that entails.

New comment by dgunay in "Jack Dorsey launches Buzz to combine team chat, AI agents and Git hosting"

dgunay — Tue, 21 Jul 2026 20:35:36 +0000

Maybe this is naive or startup-brained of me: I understand not wanting HR-related things to be potentially exposed by a misaligned agent, but when it comes purely to the building of software I personally do not care at all who can read the code/discussions & engage with the process.

New comment by dgunay in "Claude Code(Fable) refused my slow down instruction"

dgunay — Sat, 18 Jul 2026 06:40:07 +0000

I haven't tried fable in this role yet but overall I've found most models to have a preferred way of doing orchestration tasks and in general do not consistently follow instructions that tell them to work in a certain way. Especially trying to tell them to do tool use with verbal restrictions just never worked for more than a few turns. Much more effective to blacklist certain commands/patterns with a reminder hook since they will always fall back into their weights over time.

New comment by dgunay in "How to stop Claude from saying load-bearing"

dgunay — Tue, 14 Jul 2026 20:01:59 +0000

I'm guilty of this too, but at least my speech tics are mostly a unique blend to me, and they also tend to change seasonally. Meanwhile the emdashpocalypse has been going on for years.

New comment by dgunay in "DMS 1.5 "The Wolverine" Released"

dgunay — Mon, 13 Jul 2026 19:10:40 +0000

DMS is a pretty good gateway drug out of major DEs and into WMs like Niri. I had already started using Niri but the base DMS configuration has a lot more batteries included so I switched and so far haven't had any major complaints.

New comment by dgunay in "Fintech Engineering Handbook"

dgunay — Sun, 28 Jun 2026 05:18:45 +0000

That's definitely valid, for b2c applications though a lot of the time you will never deal with numbers of that magnitude.

New comment by dgunay in "Fintech Engineering Handbook"

dgunay — Sat, 27 Jun 2026 22:03:09 +0000

All of the data we control (in the database, in our apis, etc) is integer cents. When we have to interface with a system that represents money using JSON numbers as dollars.cents, we parse or serialize it into an arbitrary precision decimal type. Hasn't been much of a problem.

New comment by dgunay in "Codex logging bug may write TBs to local SSDs"

dgunay — Mon, 22 Jun 2026 23:12:51 +0000

Maybe I'm just not aware enough to notice any quality degradation, but I've been using Claude Code in repos that only have AGENTS.md and it just generally seems to know to read it when getting its bearings.

New comment by dgunay in "USB Power Delivery: Plugging into the Benefits"

dgunay — Sun, 14 Jun 2026 22:54:25 +0000

I have one and it's such a fantastic design. When I need to travel I just throw a tiny puck in my bag and it charges off the same brick that charges everything else I bring.

New comment by dgunay in "I stopped tracking my time. Now I can't focus"

dgunay — Thu, 11 Jun 2026 21:22:20 +0000

I spent a few months doing some coarse time tracking at work - basically I'd retroactively add and edit events on my calendar to reflect what I had actually done during the workday, down to 15 minute increments. I binned them into IC work, meetings, interruptions, and non-work stuff. While I did get some insights about where my time was going, it mostly just made me really anxious and input-oriented about my productivity and made feel guilty if I didn't end up working a full 8 hours on a given day. Stopping the time tracking was good for my mental health.

Show HN: Remuda, a CLI Agent Orchestrator

dgunay — Thu, 11 Jun 2026 18:19:05 +0000

Hi HN, I recently open sourced a small tool (Remuda) that I built at work to remove some of the friction of launching and managing agents and figured HN might be interested.

I also wrote a post on the company blog that goes into more detail about why I built it and showcases its features: https://www.yendo.com/blog/remuda-an-agent-orchestrator

Comments URL: https://news.ycombinator.com/item?id=48494340

Points: 5

# Comments: 0

New comment by dgunay in "Claude Fable 5"

dgunay — Tue, 09 Jun 2026 21:07:33 +0000

I'm a little skeptical of claims like this that involve migrating things like libraries, etc. I've done big refactors like this multiple times (albeit, in an "only" 500k-1m LOC codebase) with less powerful models and it is usually just 99% the same edits, with 1% requiring a close human eye to resolve a particularly painful breaking change.

EDIT: to be clear, it's still quite a helpful thing in terms of time saved, I just don't think it's necessarily the best indication of value-added from making models smarter when cases like this can often be handled by well-directed swarms of smaller ones.

New comment by dgunay in "Ask HN: What are tools you have made for yourself since the advent of AI?"

dgunay — Tue, 09 Jun 2026 08:12:56 +0000

Mostly I was not an "I have a script for that" guy before AI, except for the occasional VERY simple or VERY high ROI thing. Now I've got more oddball scripts that do things I couldn't be bothered to automate before, including: workarounds for buggy software, stitching tmux together with other tools, automating common operations so I don't have to use the god awful GitHub UI, etc.

New comment by dgunay in "Ask HN: What was your "oh shit" moment with GenAI?"

dgunay — Sun, 07 Jun 2026 07:06:34 +0000

Not an "oh shit" per se, but Gemini is a complete leap in terms of actual smarts over Google Assistant.

I was having problems getting it to parse my speech correctly when I was asking about "autolyse" (I was attempting to bake bread). All I had to do to fix it was add this to the system prompt: " I primarily interact with you via a speech to text mechanism. You should consider ways in which my words may not be accurately transcribed and attempt to infer the correct reading in context. When you do this, do not mention it - just proceed as if my words were recorded properly."

Never had that problem again. With Assistant though, if I had any issue like that I'd be waiting months or years for a fix, if it ever came.