Feed aggregator

Article URL: https://www.youtube.com/watch?v=OBJZw3bF0dg

Comments URL: https://news.ycombinator.com/item?id=49904117

Points: 2

# Comments: 0

Article URL: https://www.fateshow.site

Comments URL: https://news.ycombinator.com/item?id=49904113

Points: 1

# Comments: 0

One topic I've been researching lately is the best way to handle switching to another agent when I hit a usage limit on one of them. For example, if I hit the usage limit on Codex, I would want to switch to Claude Code and vice versa.

The important part is not losing the ongoing context/task(s) when switching between the tools.. I have found a few things that say they do this but none seem to have much traction.

As a result, I was hoping to pick the brain of HN'ers to see how you all handle this

(To head off comments regarding 'pay for a better plan for more usage' - I can't currently really afford the jump from $20 a month per agent to $100-200/m per agent)

Comments URL: https://news.ycombinator.com/item?id=49904074

Points: 1

# Comments: 1

Article URL: https://blog.google/products-and-platforms/devices/googlebook/henry-cavill-googlebook-video-game/

Comments URL: https://news.ycombinator.com/item?id=49904032

Points: 2

# Comments: 0

Article URL: https://github.com/Sparticle62ops/pssa

Comments URL: https://news.ycombinator.com/item?id=49903993

Points: 12

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Radiofax

Comments URL: https://news.ycombinator.com/item?id=49903989

Points: 2

# Comments: 0

Article URL: https://siliconpalace.substack.com/p/the-adolescence-of-the-state

Comments URL: https://news.ycombinator.com/item?id=49903968

Points: 2

# Comments: 0

Article URL: https://www.raphnet.net/radio/wefax/index_en.php

Comments URL: https://news.ycombinator.com/item?id=49903924

Points: 4

# Comments: 1

Article URL: https://github.com/BerriAI/litellm/security/advisories/GHSA-7hp6-4w63-5g45

Comments URL: https://news.ycombinator.com/item?id=49903923

Points: 1

# Comments: 0

Article URL: https://terrytao.wordpress.com/2026/09/26/a-value-based-approach-to-mathematics/

Comments URL: https://news.ycombinator.com/item?id=49903918

Points: 1

# Comments: 0

Article URL: https://spacenews.com/astroforge-to-test-full-spacecraft-autonomy-using-ai/

Comments URL: https://news.ycombinator.com/item?id=49903884

Points: 1

# Comments: 0

Article URL: https://github.com/deepseek-ai/DeepGEMM-Ascend

Comments URL: https://news.ycombinator.com/item?id=49903881

Points: 1

# Comments: 0

Article URL: https://lfm.xiffy.nl/

Comments URL: https://news.ycombinator.com/item?id=49903862

Points: 2

# Comments: 1

Article URL: https://fortune.com/2026/09/24/travis-kalanick-uber-comeback-atoms-ai-robotics-cloud-kitchens-silicon-valley/

Comments URL: https://news.ycombinator.com/item?id=49903854

Points: 1

# Comments: 1

Article URL: https://jacobg.co/copilot/

Comments URL: https://news.ycombinator.com/item?id=49903853

Points: 1

# Comments: 0

Article URL: https://github.com/yeet-src/omarchy-yeet-ai

Comments URL: https://news.ycombinator.com/item?id=49903831

Points: 1

# Comments: 0

Article URL: https://billmckibben.substack.com/p/amazon-crime

Comments URL: https://news.ycombinator.com/item?id=49903829

Points: 1

# Comments: 0

Article URL: https://asawicki.info/news_1757_a_metric_for_memory_fragmentation

Comments URL: https://news.ycombinator.com/item?id=49903803

Points: 1

# Comments: 0

Watched a recent youtube veritasium on the enigma machine and was curious on how JEV would do in regards to the analysts calls made at Bletchley's. I rebuilt the historical sequence into the software ux.

Results were a mixed, which is what made it interesting. Given the right crib, the Bombe breaks 22 of 25 messages; ciphertext-only against 10 plugs, 0 of 25, same wall Bletchley hit. As a judge of "is this decryption German?" Jev is excellent: AUC 0.9999, 159/160 right decisions. As a crib selector it has no skill at all; its ranking is no better than the fixed list.

Against XGBoost an classical judges, it ties on the same kind of data. But trained on synthetic traffic and tested on real intercepts, and XGBoost drops to 53% correc versus zero-shot Jev holds at 97%. Feel free to try it here: https://enigma-jev.vercel.app/ (requires a jev typesafe api key)

Comments URL: https://news.ycombinator.com/item?id=49903792

Points: 1

# Comments: 0

Article URL: https://github.com/biplabku/nats-lens

Comments URL: https://news.ycombinator.com/item?id=49903782

Points: 1

# Comments: 0