Hacker News: calgoo

New comment by calgoo in "Mistral Large 4"

calgoo — Tue, 06 Oct 2026 13:41:50 +0000

Please, give it another 6 months and they catch up. The American labs are currently trying everything they can to block others instead of advancing their models, trying to build an artificial moat. The American models are not that great, they are good, and they have a lot of agentic workflows in the back, but its basically a hardware limitation at this point. Once the HW makers catch up, and we can move away from the Nvidia monopoly, things will speed up quite a lot IMO.

New comment by calgoo in "Anthropic reported diary entry to police, woman faces felony charge"

calgoo — Mon, 05 Oct 2026 06:43:22 +0000

Yes but you are someone (i assume because you are on HN) that at least understands this point. There are A LOT of people that use it as their confidant, expecting it to be private. There is a massive education issue going on as its not in the interest of these Corpos to make you fear sharing all your details with them. Because, then you wont get Dot or whatever Anthropic comes up with and share all your personal info with it.

New comment by calgoo in "Tesla takes on $30B in credit as it approaches unprofitability"

calgoo — Wed, 30 Sep 2026 05:54:29 +0000

That last part is a big thing, especially in Europe where a lot of their sales have almost stopped as no one wants to drive a nazi car.

New comment by calgoo in "America.gov"

calgoo — Tue, 29 Sep 2026 21:21:46 +0000

Actually quite interesting that there is no good naming for people from the USA. Its just the patriotic BS that has spewed over there for decades that has lead to USA people believing they are the only Americans :)

New comment by calgoo in "America.gov"

calgoo — Tue, 29 Sep 2026 21:17:48 +0000

Well, lets discuss the name? America is a big place, and the USA is small part of it. USA.gov? Good, America.gov? Very political in nature.

New comment by calgoo in "Mercury 2.5 LLM hits 770 tokens per second"

calgoo — Thu, 24 Sep 2026 08:03:04 +0000

You can, but you need to break the problem into much smaller tasks, then check those answers, and finally have a harness that handles all the context, task breakup, task definitions, and validations each round.

New comment by calgoo in "Mercury 2.5 LLM hits 770 tokens per second"

calgoo — Thu, 24 Sep 2026 07:58:26 +0000

No you dont need to code at 600 w/s BUT at those speeds, you can start doing things like asking multiple different agents the same question and picking the best solution each time without noticing the lag.

New comment by calgoo in "Pentagon says overreliance on AI contributed to missile strike on Iran school"

calgoo — Wed, 23 Sep 2026 08:35:38 +0000

The whole point of using the AI systems it to review vast amount of data. They would 100% have access to updated pictures if we as civs can pull that data from public sources. Its not like the school was new, it had existed for over 10 years!!

[1]https://www.bbc.com/news/articles/c5yqqyly9n0o

New comment by calgoo in "Elevated errors for multiple models – Resolved"

calgoo — Tue, 22 Sep 2026 05:57:24 +0000

Not sure what the problem with switching is? When I run out of my kimi session, I just switch model and tell deepseek to continue. Yes I eat the initial cache miss but that's it, no fancy harness required.

New comment by calgoo in "AX – Google’s Open Agentic Orchestrator"

calgoo — Mon, 21 Sep 2026 08:31:41 +0000

Yes thats fine, but i would never trust to use one of their productions in production so to speak.

New comment by calgoo in "Spain Orders Blocks on Archive.today and Its Mirrors"

calgoo — Sun, 20 Sep 2026 08:07:17 +0000

This is working fine for me in spain so far....

New comment by calgoo in "HarnessTax: How Much Does the Harness Matter for Coding Agents?"

calgoo — Thu, 17 Sep 2026 06:24:23 +0000

I really disliked how opencode works IMO; the harness tries to do to much in my mind. Switching to Pi was a breath of fresh air for me, and I even use hax for some of my local needs where i dont want to have the giant pile of fertilizer that is NPM or PIP installed.

The harness becomes more and more important, the smaller the model is as you need to offload context management as well as memory to the harness. The big models basically just need a bash prompt tooling and you let the model manage everything inside its own context.

New comment by calgoo in "Mistral X Mozilla: Private, Multilingual AI Browsing"

calgoo — Thu, 17 Sep 2026 06:18:28 +0000

Dont use this for work unless it has been verified by your corporate security and legal teams. Sharing business data with a company with which you dont have a enterprise agreement can land you in serious trouble.

New comment by calgoo in "Hackers Got Inside a Flock Camera. Its Data Shows How the System Works"

calgoo — Wed, 16 Sep 2026 14:26:06 +0000

Because we got the gray box IBM version instead...

New comment by calgoo in "Suspected sabotage causes major Netherlands rail disruption"

calgoo — Wed, 16 Sep 2026 08:59:59 +0000

Just Like Saab in Sweden, except Saab dont sell any cars anymore unfortunately.

New comment by calgoo in "A single firm is behind OpenAI, Anthropic, and Meta hacking scandals"

calgoo — Tue, 15 Sep 2026 19:03:30 +0000

Also dont forget that HF is now owned by Nvidia, which can then control the flow of the majority of models and only allow the approved models that have paid their due in trump coins.

New comment by calgoo in "Everyone should slow down AI development except for me"

calgoo — Sun, 13 Sep 2026 08:34:13 +0000

The danger lies with someone asking the machine to solve those two questions and it decides to cheat the solution. Launching every nuke in the world stops all wars, just like wiping out 99% of humanity ends world hunger.

New comment by calgoo in "Everyone should slow down AI development except for me"

calgoo — Sun, 13 Sep 2026 08:31:48 +0000

Or you know, stop working on it if its that dangerous? This whole thing of a bunch of employees saying that they are scared of building what they are building, but do it anyway because they are somehow going to make it different? Their model has been used in the planning of mass murdering in war as well as spying on the entire worlds population as well as helping ICE out in the US. They need to stop this BS fearmongering or actually stand up and do something about it. A government regulation is not the answer, especially when its done in a country that is run by a want to be dictator.

New comment by calgoo in "DeepSeek v4.1 Flash"

calgoo — Thu, 10 Sep 2026 08:08:08 +0000

Yes, this is one of the few issues with Deepseek; their chat pages and the app all respond in Chinese. However, i think i have only had it happen once when using the API, and im using it for hours each day for the last... couple of months?

New comment by calgoo in "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"

calgoo — Wed, 09 Sep 2026 12:44:49 +0000

v4 flash has been working quite well for the majority of my personal projects, with occasional v4 pro or Kimi 3 for the most complicated tasks or to check the overall project progress (when vibe coding).