Hacker News: ttoinou

New comment by ttoinou in "A Visual Intro to Complex Numbers"

ttoinou — Tue, 13 Oct 2026 19:46:15 +0000

Of course maths need intuition, it isn’t always incompatible with being rigorous

But yes some who have PhD in physics don’t always care about understanding deeply maths tools. Depends what you’re doing

New comment by ttoinou in "A Visual Intro to Complex Numbers"

ttoinou — Tue, 13 Oct 2026 17:12:45 +0000

You can absolutely deal with complex numbers with the (x,y) notation

New comment by ttoinou in "A Visual Intro to Complex Numbers"

ttoinou — Tue, 13 Oct 2026 17:12:03 +0000

You can use exponential with matrices as well.

That some people don’t want to understand deeply the tools they use don’t make their tools superficial or “hotfixes”

New comment by ttoinou in "Intel D270 GPU AI Accelerator–Up to 480 GB LPDDR5X"

ttoinou — Tue, 13 Oct 2026 15:00:35 +0000

Get a m5 pro mac with 48gb vram and you’re good to go for a few years and that computer can be used for others purpose as well

New comment by ttoinou in "A Visual Intro to Complex Numbers"

ttoinou — Tue, 13 Oct 2026 14:17:17 +0000

I recommend Visual Complex Analysis by Tristan Needham

New comment by ttoinou in "Auto Research: Integer multiplication below n log n"

ttoinou — Tue, 13 Oct 2026 07:23:14 +0000

Have we settled on a really good universal approximation model of memory+computation or is this a hard topic to solve in itself ?

New comment by ttoinou in "Food processing influences metabolism and brain activity"

ttoinou — Sun, 11 Oct 2026 15:19:43 +0000

Calories don’t exist and it is unscientific to believe in them

New comment by ttoinou in "Show HN: Arcadeia – A self-hosted media library with animated video previews"

ttoinou — Wed, 07 Oct 2026 10:29:59 +0000

Literally just built this with claude this week to handle all outputs of my GPU generating videos and images

New comment by ttoinou in "LeCun has "zero concerns" about AI wiping out humanity, recent "rogue" incidents"

ttoinou — Mon, 05 Oct 2026 12:29:10 +0000

AGI doesn't mean Omniscience

New comment by ttoinou in "LeCun has "zero concerns" about AI wiping out humanity, recent "rogue" incidents"

ttoinou — Mon, 05 Oct 2026 12:28:28 +0000

What ? If that experiment was done on monkeys I don't think they had to use Android / iOS / iPadOS interface themselves. All they had to do is push a button

New comment by ttoinou in "From the creator of Redis; run LLM locally with ds4"

ttoinou — Sat, 03 Oct 2026 17:47:16 +0000

Oh that’d be nice indeed

New comment by ttoinou in "From the creator of Redis; run LLM locally with ds4"

ttoinou — Sat, 03 Oct 2026 00:29:40 +0000

Lots of small details are taken care of so it runs smoothly. For example ds4-agent is append only, never rewriting history of messages, keeping KV cache prefix reusable. Huge benefit

New comment by ttoinou in "From the creator of Redis; run LLM locally with ds4"

ttoinou — Fri, 02 Oct 2026 22:20:11 +0000

I’m already able to use 1M context windows with the same machine than you and same model. Strange

New comment by ttoinou in "From the creator of Redis; run LLM locally with ds4"

ttoinou — Fri, 02 Oct 2026 22:19:03 +0000

Ive been using this since it was initially released with deepseek v4 flash, and it is absolutely the best launcher ever on my m5 max 128gb

Now Ive been running qwen 3.8 flash next for more than a week and it’s doing great, really fast and super long context windows. Sometimes the model is behaving stupidly by not remembering something I said earlier but it could be also a problem from the agentic AI harness. Im using oh my pi but Im wondering what people are using ds4 with here ?

New comment by ttoinou in "macOS 27 is so buggy"

ttoinou — Thu, 01 Oct 2026 18:47:48 +0000

The reality is probabilistic, and engineering has always been about turning that into deterministic behavior and outcomes, in an industrial, repeatable, observable, debuggable way

New comment by ttoinou in "macOS 27 is so buggy"

ttoinou — Thu, 01 Oct 2026 18:46:45 +0000

I wouldn’t call Chrome a pile of shit software. If anything else we should learn from this project

And the web is the most advanced and open OS in the world. That all those features can be packaged into a 100MB binary is magic

New comment by ttoinou in "Turning GLM-5.3-Flash into a Jev-like decision model"

ttoinou — Sun, 27 Sep 2026 01:34:02 +0000

Isnt this obvious ? I would have thought people would try such things before deciding they need something like Jev

New comment by ttoinou in "Show HN: Foremerge – Catch intent conflicts between parallel coding agents"

ttoinou — Tue, 22 Sep 2026 01:47:34 +0000

I doubt this can really be deterministic, but maybe this is where Jev models can be useful

New comment by ttoinou in "Show HN: Foremerge – Catch intent conflicts between parallel coding agents"

ttoinou — Tue, 22 Sep 2026 00:37:10 +0000

   Before editing each agent publishes an intent and the scopes it will change, with the operation it plans to complete on each one.

But we don't know in advance what we will need to change in our current task. And even if we did, there are always side effects.

New comment by ttoinou in "Show HN: Foremerge – Catch intent conflicts between parallel coding agents"

ttoinou — Tue, 22 Sep 2026 00:36:21 +0000

I'm curious to know what's everyone custom solution to this problem ? Before AI and with AI.

It was already a problem for me before agentic AI coding : multiple developers can work on overlapping code and you always need someone to merge everything properly. Even if the overlap is very small it does add a burden to development. Not an issue anymore in 95% of cases if that person uses AI to solve conflicts, but now that "others developers" are swarm of AI agents, this problem isn't trivial to solve.