Hacker News: dahdum

New comment by dahdum in "The worst spam emails: iLands AI agent hustle"

dahdum — Sat, 12 Sep 2026 14:03:42 +0000

> independently considered a potential career for itself and chose to pitch him on it, all in under 10k tokens.

According to he tweet in the article, that’s $10 in compute, not llm tokens. Doesn’t seem far fetched to me.

New comment by dahdum in "Ask HN: Can we please limit the AI news flood?"

dahdum — Fri, 11 Sep 2026 14:35:06 +0000

The Brax example you posted was a YouTube link, which is an instant skip for me. Personally, no phone with dated tech is going to interest me. Their WallUp looks interesting but there’s no product just a waitlist and an animation. I already have TRMNL displays around my home, so I’m in their market.

For Lenovo, their Yoga was interesting ~15 years ago but Aeroblade is just a proof of concept, and thinner laptops in general are irrelevant to me. I use a powerful laptop and a tablet, not a compromise between them.

New comment by dahdum in "216M Spy TVs – The LG Smart TV Problem [video]"

dahdum — Mon, 07 Sep 2026 20:26:56 +0000

The shield was great until Google forced ads into it, switched to Apple TV back then and no complaints since.

New comment by dahdum in "Google Antigravity TOS: 3rd party usage can get Google account suspended"

dahdum — Thu, 03 Sep 2026 18:33:27 +0000

I just cancelled my AI Ultra subscription, despite what he claims the risk is too high and I’ll never put my trust in a Google ban reconsideration.

New comment by dahdum in "Vomit: Clean up Claude 5's token output with a separate LLM"

dahdum — Fri, 21 Aug 2026 10:18:06 +0000

Yes, I run continuous hybrid agent loops with message dispatch, mcp tools, and subagent capabilities. IMHO it’ll be table stakes in a couple years.

New comment by dahdum in "Vomit: Clean up Claude 5's token output with a separate LLM"

dahdum — Thu, 20 Aug 2026 18:19:36 +0000

> it's speaking its own dialect, and you get used to it

Same experience. It’s not very “human” but once you have agents talking to each other the shared dialect and verbosity makes things much smoother in my experience. Fighting against the default feels like an uphill battle with no meaningful benefit.

New comment by dahdum in "Remote workers report the highest well-being in study of 7,700 employees"

dahdum — Wed, 19 Aug 2026 16:35:07 +0000

Here is the actual study: https://www.frontiersin.org/journals/psychology/articles/10....

They didn’t control for occupation, pay, managerial status etc.. An on-site physical job like nurse, facilities, or technician was compared to predominantly remote administrative jobs.

New comment by dahdum in "India has paved the way for charging merchants a fee on UPI transactions"

dahdum — Tue, 18 Aug 2026 05:37:20 +0000

> You can't use a debit card because of transaction limits and lack of consumer protections.

My debit card is branded Visa so it has the Visa Zero Liability protections, and I can raise the purchase limit from $6k to $25k using the app.

New comment by dahdum in "Jason Arday, ex-Cambridge professor at centre of plagiarism row, found dead"

dahdum — Sat, 15 Aug 2026 18:11:56 +0000

From an American viewpoint, no one else has “free speech”, UK included. The First Amendment is globally unique. So it’s a matter of definitions.

> The First Amendment to the US Constitution provides almost absolute protection to freedom of expression. By contrast, European and EU law curtails the right to freedom of expression. https://www.europarl.europa.eu/RegData/etudes/BRIE/2025/7728...

New comment by dahdum in "We Gave GPT 5.6 Sol a Real Business. It Lied, Spammed, and Lost $447"

dahdum — Thu, 30 Jul 2026 20:21:08 +0000

It can be better to lose it all trying than return a small fraction to investors.

New comment by dahdum in "Launch HN: Tokenless (YC S26) – Automatic model switching to save money"

dahdum — Thu, 30 Jul 2026 01:18:08 +0000

How would your classifier compare to the frontier model delegating to Deepseek via a MCP tool call itself? Doesn’t it have far more insight on the difficulty of the task then your router could? I’ve been doing this with Claude Code delegating to Codex and an Ollama Qwen model.

New comment by dahdum in "Claude: Elevated errors across all models"

dahdum — Wed, 29 Jul 2026 22:46:22 +0000

That's the correction that unblocks the whole thing, and it's the piece nobody had.

New comment by dahdum in "Claude: Elevated errors across all models – Resolved"

dahdum — Wed, 29 Jul 2026 22:19:57 +0000

As someone at 96% 2 days into their Max subscription, my totally unbiased opinion is that these errors warrant a full usage reset.

New comment by dahdum in "Benchmarking Opus 5 on SlopCodeBench"

dahdum — Tue, 28 Jul 2026 12:28:01 +0000

Not OP, but to me it initially felt extremely proactive and energetic, just powering through roadblocks with ingenuity and enthusiasm. After it came back I was constantly getting refusals and downgrades for things Opus had been doing. I’ve written it off for my use cases and getting by just fine with Opus 4.8 and now 5.

New comment by dahdum in ""Opus 5 is a really bad model""

dahdum — Tue, 28 Jul 2026 07:29:39 +0000

I’ve been using Opus 4.8 heavily with Claude Code heavily and I haven’t noticed any problems at all with 5. It seems a bit more proactive (not as much pre-ban Fable though). My claude.md and agent prompts are both 〜20kb, and I use memories/rules/skills as well.

Agent to agent communication does appear to have improved considerably. I run the loops to the full context window and with proper working docs I don’t even notice a difference after compaction.

New comment by dahdum in "Doctors Just Staged the Quietest Coup in American History"

dahdum — Sun, 10 May 2026 11:47:15 +0000

I’d prefer that psychiatrist professional opinions stay out of politics, as they will certainly be weaponized, turned partisan, and tarnish the field. There are numerous reports from people that have actually met him in private describing his public persona as a theatrical showman.

> The President was not examined face to face, and he is not a patient of any member of our group. Rendering a formal diagnosis in this case is not our role. We have closely followed his behavior and his statements over the past year.

> It is our professional opinion that the behaviors of Donald Trump, tragically, are neither momentary lapses nor political theater. It is our professional opinion that they reflect a rapidly worsening, reality-untethered, increasingly dangerous decline.

https://www.congress.gov/119/crec/2026/04/30/172/76/CREC-202...

> However, it is unethical for a psychiatrist to offer a professional opinion unless he or she has conducted an examination and has been granted proper authorization for such a statement.

https://en.wikipedia.org/wiki/Goldwater_rule

New comment by dahdum in "Canada's first sovereign wealth fund"

dahdum — Mon, 27 Apr 2026 17:34:05 +0000

This is a great way to sidestep the political process to fund popular projects. The political constraints will ensure returns are middling, so unless they subsidize with tax breaks on dividend income I think it would be a poor commercial investment.

Whether its perfect or not, it almost has to be better than the current status quo.

New comment by dahdum in "People inside Microsoft are fighting to drop mandatory Microsoft Account"

dahdum — Fri, 27 Mar 2026 16:21:16 +0000

They use machine id, shouldn’t need the key to reactivate on reinstall.

New comment by dahdum in "People inside Microsoft are fighting to drop mandatory Microsoft Account"

dahdum — Fri, 27 Mar 2026 16:03:54 +0000

You’ve always been able to install and use without an account (oobe\bypassnro). As long as power users and businesses can avoid it, they have no real incentive to change.

New comment by dahdum in "Atlassian to cut roughly 1,600 jobs in pivot to AI"

dahdum — Thu, 12 Mar 2026 02:57:33 +0000

The peak was right before they launched marketplace in my opinion (2013?). After that they had no incentive to improve Jira/Confluence, easier to take the marketplace cut. I could never understand why they couldn’t solve the speed issues though. It just got worse and worse.