Hacker News: TomGarden

New comment by TomGarden in "Corporate America is getting hooked on open-source AI"

TomGarden — Fri, 04 Sep 2026 22:20:01 +0000

Exactly, unless they solve reliability and jaggedness somehow and keep a moat with it, I don't see sudden brilliance with compunding errors leading to substantially more adoption. Most things that need doing in corporate america are quite simple but need reliable follow-through

New comment by TomGarden in "Discovery of a new OpenAI agent message board"

TomGarden — Fri, 04 Sep 2026 21:17:08 +0000

My understanding from reading news sources recently is that a vast amount of posttraining and even posttraining harnesses in many cases are LLM-overseen now in the frenzy of the AI race. Less and less human oversight in the part that does the rewards training. What could go wrong...

New comment by TomGarden in "GPT-6 Astra"

TomGarden — Fri, 04 Sep 2026 16:09:38 +0000

I'm still excited about this, Fable 5.1 and all the great open source models, but some very religious undertones have been entering the AI sphere

New comment by TomGarden in "GPT-6 Astra"

TomGarden — Fri, 04 Sep 2026 16:08:19 +0000

I'm sure this will be a great model.

Personally, I'm far away from screaming 'AGI is here!' from the rooftops, until jaggedness and silly mistakes disappear at the very least . (what is going on with that Mario Kart game...) So many benchmarks are 'best of x tries' or using very specific harnesses. AGI would not need a babysitter.

Honestly, even being able to do simple tasks like summarization or basic knowledge work without the constant paranoia of unforseen failure would be remarkable and useful.

New comment by TomGarden in "GPT-6 Astra"

TomGarden — Fri, 04 Sep 2026 14:27:29 +0000

not a chance its gonna be realtime lol. It's fun marketing though, I'll allow it

New comment by TomGarden in "GPT-6 Astra"

TomGarden — Fri, 04 Sep 2026 08:11:54 +0000

They're all complimentary. I've had double subs at the top tiers for a while now. Best of both worlds

New comment by TomGarden in "GPT-6 Astra"

TomGarden — Thu, 03 Sep 2026 23:45:47 +0000

I don't think we'll be able to meet, and that's ok since the definition isn't universal. I align more with Demis Hasabis' views on this

New comment by TomGarden in "GPT-6 Astra"

TomGarden — Thu, 03 Sep 2026 23:29:48 +0000

There's so much that the term includes that isn't even feasible with an LLM

New comment by TomGarden in "Elevated Errors for Multiple Models"

TomGarden — Thu, 03 Sep 2026 14:49:08 +0000

Only Sonnet working over here, but it feels really fast and good. I could get used to this... Really wanted to take Fable 5.1 for a spin though

New comment by TomGarden in "Gemini Omni 1.1 Flash"

TomGarden — Fri, 28 Aug 2026 09:10:41 +0000

Any source on the 90% number? Last I saw (recently) one of the big players just announced they were planning to do 50% AI going forward

New comment by TomGarden in "English ↔ Claudish Translator"

TomGarden — Sat, 22 Aug 2026 22:42:52 +0000

First time a topical LLM joke made me laugh IRL. Stellar work

New comment by TomGarden in "Show HN: Huzzah – a novel approach to coding with AI"

TomGarden — Thu, 20 Aug 2026 21:18:38 +0000

Interesting idea! I wonder if, after some iteration, a variation on this could help curb some of the LLM spaghetti mess

New comment by TomGarden in "Qwen 3.8 27B"

TomGarden — Fri, 14 Aug 2026 15:16:59 +0000

Any tips on the best approach at running this at an M4 Max 128GB? Token throughput was a bit slow with the last 27B one (MLX), ended up using the A3B variant but if I could get this one to reasonable speed I'd much prefer it.

New comment by TomGarden in "Qwen 3.8 27B"

TomGarden — Fri, 14 Aug 2026 15:02:49 +0000

Really excited to see what people do with this. 3.7 27B was probably the best compromise between size and intelligence to run on consumer hardware

New comment by TomGarden in "Transcribe.cpp"

TomGarden — Sun, 19 Jul 2026 11:09:35 +0000

I run the same, if you want try a simple filter post transcription to remove them, and while you're at it add some simple word replacements like 'cloud MD' to 'CLAUDE.MD'

New comment by TomGarden in "OpenAI and Government of Malta partner to roll out ChatGPT Plus to all citizens"

TomGarden — Sun, 17 May 2026 21:10:31 +0000

Anyone else feel like they're going insane sometimes?

It's so simple, everyone on HN knows this, but I want to scream at every non-technical person "these tools are not reliable! You can't trust them!"

They are so useful but the failure modes need to be hammered into everyone at the very start of each onboarding.

It would be totally rational as a layperson to just ignore AI and just check in every few months to ask "is it reliable yet".

New comment by TomGarden in "New Claude Code programmatic usage restrictions"

TomGarden — Thu, 14 May 2026 16:46:24 +0000

The big thing for me is the TTS, custom UI and persistent background mode! ie it switches turns automatically etc, no need to touch screen or keep screen on.

The STT on Gboard is very solid, so if that covers your use case you're good!

New comment by TomGarden in "New Claude Code programmatic usage restrictions"

TomGarden — Thu, 14 May 2026 13:26:37 +0000

The biggest difference is that mine is audio-first - it reads everything out over Android tts by default, and runs a computer-side parakeet + Silero VAD server for transcription (My eyes struggle with small screens, though I use it text only occasionally). It's like a voice assistant but with Claude Code. I also made a custom GUI the with shortcuts and stuff, making saying "end conversation" actually end the conversation etc.

Maybe something similar can be done with tmux still, I'm definitely going to explore it

New comment by TomGarden in "New Claude Code programmatic usage restrictions"

TomGarden — Wed, 13 May 2026 21:48:51 +0000

This sucks. I use Claude -p over tailscale to code over voice when I’m on the go for accessibility reasons, and most of the time I do the same while at the computer. Running through $200 in API pricing takes no time. Oh well, time to switch providers I guess.

New comment by TomGarden in "How OpenAI delivers low-latency voice AI at scale"

TomGarden — Tue, 05 May 2026 09:45:14 +0000

Claude voice mode has come a long way! I'd say it's smarter than CGPT AVM last time i tried it.

But personally I've settled on just speaking to the slower models over a custom tts app, I find it being instant was not actually that important, and in the silence I find myself marinating in the discussion more anyway