northern-lights

Joined 7 years ago

Karma
346
Submissions
93
Member since
Nov 15
View on Hacker News

Recent submissions

Comment · 1 month ago
Networking companies (like Cisco, HPE etc.) do this all the time with their test beds deliberately disconnected from internet. It's not hard.
Comment · 2 months ago
Unfortunately, I don;t think that can ever be fixed. For an LLM to know that it is not hallucinating about something, it must know that that statement(s) is/are true. Which it cannot infer due to Godel's Incompleteness theorems.
Comment · 2 months ago
I had the same problem - Opus models past 4.7 tend to inflate output tokens for no good reasons, introduce innumerable jargons and is a pain to read. Then, I cam across this: https://github.com/ayghri/i-have-adhd/blob/main/skills/i-hav...

You can either install that skill or put the Rules section directly in your Global CLAUDE.md for Claude or Personalization setting for Codex and it should cut down the output verbosity by quite a fair bit.

Comment · 5 months ago
> Not only that, but we plan to release a new class of model with even higher intelligence than Opus. As part of Project Glasswing, a small number of organizations are currently using Claude Mythos Preview for cybersecurity work. Models of this capability level require stronger cyber safeguards before they can be generally released. We’re making swift progress on developing these safeguards and expect to be able to bring Mythos-class models to all our customers in the coming weeks.

Probably more interesting than the 4.8 release.

Comment · 5 months ago
Because with Max subscriptions, you have to use the Claude Agent SDK, which is basically running Claude Code underneath. You don't get to use the chat/Messages APIs with personal subscriptions, for that you need the API pricing.
Comment · 6 months ago
How many?
Comment · 6 months ago
Then, I suggest that you educate yourself on how unions function and what they do. It's not my job to educate you. You can also ChatGPT this by the way.
Comment · 6 months ago
It does not limit hiring in any way.

As for what solutions union provide - I have already explained. They exist to protect workers' interests. They do not exist to solve company's problems. That is the job of the company.

Comment · 6 months ago
The point of a union is not prevent layoffs and role reduction in force. It is to make sure that the company has done its absolute best to find another solution to the problem (that they're trying to solve with layoffs) and ensures that the company is accountable for all their decisions.
Comment · 6 months ago
A union's objective is to protect and safeguard the interest of its members. As long as it does that, it adds value, regardless of what anyone else (especially those not in the union) thinks whether it has value.
Comment · 6 months ago
What has unionizing and society caring have got to do with each other?
Comment · 6 months ago
This thread is filled with so many anti-union takes that you have to wonder if they are paid bots.

If you assume that most of the crowd that visits this website works in tech or tech-adjacent fields, how can you be against an entity whose main objective is to safeguard and work for your interests over your employers? Unfathomable that people are willing to do so much against their own best interests. Or...they are bots.

Comment · 6 months ago
Why do you think Google considers Anthropic a competitor?
Comment · 6 months ago
Encryption can only ensure the confidentiality of a message from a non-trusted third party but when that non-trusted third party happens to be your own machine hosting Claude Code, then it is pointless. You can always dump the keys (from your memory) that were used to encrypt/decrypt the message and use it to reconstruct the model weights (from the dump of your memory).
Comment · 7 months ago
as a counterpoint - Amazon is a Java shop and most of the companies that model themselves after Amazon are also Java shops.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton