Hacker News: ttoinou

New comment by ttoinou in "We're running out of benchmarks to upper bound AI capabilities"

ttoinou — Fri, 10 Apr 2026 23:16:31 +0000

We already have specialized AI to play video games

New comment by ttoinou in "I've been waiting over a month for Anthropic to respond to my billing issue"

ttoinou — Wed, 08 Apr 2026 20:35:37 +0000

What if they built their company with poor support, so they don’t have to hold up to any standard ? But others companies have historically good reputation for good customer support, and maybe AI can help them automate easily 80% of easiest requests

New comment by ttoinou in "Revision Demoparty 2026: Razor1911 [video]"

ttoinou — Wed, 08 Apr 2026 09:52:09 +0000

Anyone understand why multiple demos have voices singing now.. how do they do it ?

New comment by ttoinou in "Revision Demoparty 2026: Razor1911 [video]"

ttoinou — Wed, 08 Apr 2026 09:50:22 +0000

Wow, and this is their “mid career retrospective”. Wait for the end of caree retrospective…

New comment by ttoinou in "Yann LeCun raises $1B to build AI that understands the physical world"

ttoinou — Tue, 10 Mar 2026 20:43:44 +0000

French people have this pipe dream all others french people to pay 75% of what they produce worldwide to pay for their retreats, hospital, useless schools system and all theirs “comité Théodule”

New comment by ttoinou in "Yann LeCun raises $1B to build AI that understands the physical world"

ttoinou — Tue, 10 Mar 2026 12:39:34 +0000

No he said something like “well yes, only for the parts of profits made in France”

New comment by ttoinou in "LLMs work best when the user defines their acceptance criteria first"

ttoinou — Sat, 07 Mar 2026 08:15:13 +0000

No but they will despise you for bringing the problem up

New comment by ttoinou in "First MacBook Neo Benchmarks Are In"

ttoinou — Fri, 06 Mar 2026 15:15:04 +0000

Using Parallels yes. Whats “on the metal” ?

New comment by ttoinou in "MacBook Pro with M5 Pro and M5 Max"

ttoinou — Tue, 03 Mar 2026 15:48:05 +0000

With M3 Max with 64GB of unified ram you can code with a local LLM, so the bar is much lower

New comment by ttoinou in "Tell HN: YC companies scrape GitHub activity, send spam emails to users"

ttoinou — Thu, 26 Feb 2026 16:42:42 +0000

Couldn’t github replace all public commits author info email by a username@author.github.com email automagically ?

New comment by ttoinou in "Show HN: Emdash – Open-source agentic development environment"

ttoinou — Wed, 25 Feb 2026 07:35:47 +0000

Yes !

New comment by ttoinou in "Show HN: Emdash – Open-source agentic development environment"

ttoinou — Wed, 25 Feb 2026 00:41:32 +0000

Will you support Gitlab Issues ?

New comment by ttoinou in "Show HN: Emdash – Open-source agentic development environment"

ttoinou — Tue, 24 Feb 2026 21:51:53 +0000

(2) sounds like a great idea if you can ensure private company data never reaches your servers, with features like remote controlling agents from a central place

New comment by ttoinou in "Show HN: Emdash – Open-source agentic development environment"

ttoinou — Tue, 24 Feb 2026 21:36:23 +0000

So, what's your business model ? Is this an YC product, or a tool you developed while working on a YC product ?

New comment by ttoinou in "Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI"

ttoinou — Tue, 24 Feb 2026 12:38:09 +0000

Great thanks ! I am so annoyed by a specific phrase which is "launching wit.exe", not funny when it could actually be talking for real about software running on your machine

New comment by ttoinou in "Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI"

ttoinou — Mon, 23 Feb 2026 15:22:01 +0000

Works for me, but sometimes there's an issue with the tool template from Qwen, past chats are changed, thus KV cache gets invalidated and it needs to reprocess input tokens from scratch. Doesn't happen all the time though

Btw I also get 42-60 tps on M4 Max with the MLX 4 bit quants hosted by LM Studio, which software do you use to run it ?

New comment by ttoinou in "Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI"

ttoinou — Sat, 21 Feb 2026 01:35:41 +0000

How much tokens per seconds are you getting ?

Whats the advantage of qwen code cli over opencode ?

New comment by ttoinou in "Ggml.ai joins Hugging Face to ensure the long-term progress of Local AI"

ttoinou — Sat, 21 Feb 2026 01:30:42 +0000

There’s this developer called nightmedia who converts a lot of models to apple MLX. I can run Qwen3 coder next at 60 tps on my m4 max. It works

New comment by ttoinou in "Infrastructure decisions I endorse or regret after 4 years at a startup (2024)"

ttoinou — Fri, 20 Feb 2026 07:02:02 +0000

Nice but how do those services combine with each others ? How do you combine notion, slack, your git hosting, linear and your CI/CD ? If there are only URLs between each others it’s hard to link all the work together

New comment by ttoinou in "Mathematicians disagree on the essential structure of the complex numbers (2024)"

ttoinou — Wed, 11 Feb 2026 16:45:11 +0000

i=0+1*i =0+1*(0+1*(0+1*(0+1*(0+1*(0+1*( ...*