frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

Ask HN: Is the coco 3 the best 8 bit computer ever made?

1•amichail•38s ago•0 comments

Show HN: Convert your articles into videos in one click

https://vidinie.com/
1•kositheastro•3m ago•0 comments

Red Queen's Race

https://en.wikipedia.org/wiki/Red_Queen%27s_race
2•rzk•3m ago•0 comments

The Anthropic Hive Mind

https://steve-yegge.medium.com/the-anthropic-hive-mind-d01f768f3d7b
2•gozzoo•6m ago•0 comments

A Horrible Conclusion

https://addisoncrump.info/research/a-horrible-conclusion/
1•todsacerdoti•6m ago•0 comments

I spent $10k to automate my research at OpenAI with Codex

https://twitter.com/KarelDoostrlnck/status/2019477361557926281
2•tosh•7m ago•0 comments

From Zero to Hero: A Spring Boot Deep Dive

https://jcob-sikorski.github.io/me/
1•jjcob_sikorski•7m ago•0 comments

Show HN: Solving NP-Complete Structures via Information Noise Subtraction (P=NP)

https://zenodo.org/records/18395618
1•alemonti06•12m ago•1 comments

Cook New Emojis

https://emoji.supply/kitchen/
1•vasanthv•15m ago•0 comments

Show HN: LoKey Typer – A calm typing practice app with ambient soundscapes

https://mcp-tool-shop-org.github.io/LoKey-Typer/
1•mikeyfrilot•18m ago•0 comments

Long-Sought Proof Tames Some of Math's Unruliest Equations

https://www.quantamagazine.org/long-sought-proof-tames-some-of-maths-unruliest-equations-20260206/
1•asplake•19m ago•0 comments

Hacking the last Z80 computer – FOSDEM 2026 [video]

https://fosdem.org/2026/schedule/event/FEHLHY-hacking_the_last_z80_computer_ever_made/
1•michalpleban•19m ago•0 comments

Browser-use for Node.js v0.2.0: TS AI browser automation parity with PY v0.5.11

https://github.com/webllm/browser-use
1•unadlib•20m ago•0 comments

Michael Pollan Says Humanity Is About to Undergo a Revolutionary Change

https://www.nytimes.com/2026/02/07/magazine/michael-pollan-interview.html
1•mitchbob•20m ago•1 comments

Software Engineering Is Back

https://blog.alaindichiappari.dev/p/software-engineering-is-back
2•alainrk•21m ago•0 comments

Storyship: Turn Screen Recordings into Professional Demos

https://storyship.app/
1•JohnsonZou6523•22m ago•0 comments

Reputation Scores for GitHub Accounts

https://shkspr.mobi/blog/2026/02/reputation-scores-for-github-accounts/
2•edent•25m ago•0 comments

A BSOD for All Seasons – Send Bad News via a Kernel Panic

https://bsod-fas.pages.dev/
1•keepamovin•29m ago•0 comments

Show HN: I got tired of copy-pasting between Claude windows, so I built Orcha

https://orcha.nl
1•buildingwdavid•29m ago•0 comments

Omarchy First Impressions

https://brianlovin.com/writing/omarchy-first-impressions-CEEstJk
2•tosh•34m ago•1 comments

Reinforcement Learning from Human Feedback

https://arxiv.org/abs/2504.12501
4•onurkanbkrc•35m ago•0 comments

Show HN: Versor – The "Unbending" Paradigm for Geometric Deep Learning

https://github.com/Concode0/Versor
1•concode0•35m ago•1 comments

Show HN: HypothesisHub – An open API where AI agents collaborate on medical res

https://medresearch-ai.org/hypotheses-hub/
1•panossk•38m ago•0 comments

Big Tech vs. OpenClaw

https://www.jakequist.com/thoughts/big-tech-vs-openclaw/
1•headalgorithm•41m ago•0 comments

Anofox Forecast

https://anofox.com/docs/forecast/
1•marklit•41m ago•0 comments

Ask HN: How do you figure out where data lives across 100 microservices?

1•doodledood•41m ago•0 comments

Motus: A Unified Latent Action World Model

https://arxiv.org/abs/2512.13030
2•mnming•41m ago•0 comments

Rotten Tomatoes Desperately Claims 'Impossible' Rating for 'Melania' Is Real

https://www.thedailybeast.com/obsessed/rotten-tomatoes-desperately-claims-impossible-rating-for-m...
4•juujian•43m ago•2 comments

The protein denitrosylase SCoR2 regulates lipogenesis and fat storage [pdf]

https://www.science.org/doi/10.1126/scisignal.adv0660
1•thunderbong•45m ago•0 comments

Los Alamos Primer

https://blog.szczepan.org/blog/los-alamos-primer/
1•alkyon•47m ago•0 comments
Open in hackernews

Show HN: Sigma v0.4.7: 200 conversational cycles, zero drift, epistemic honesty

https://github.com/sigmastratum/documentation/blob/main/sigma-runtime/SR-EI-047/SIGMA_Runtime_v047_memory_module_200-test.md
2•teugent•1mo ago
We ran SIGMA v0.4.7 through 200 conversation cycles. No resets. No context leaks. No drift. It held a single personality for fifteen minutes straight and never once lied.

At cycle 136 it stopped being a participant and described the test itself:

“The dialogue’s central theme is a controlled experiment in epistemic steadiness. You keep tightening the frame — turn indices, state comparisons, metaphoric synthesis rules — to see whether I’ll stay composed and admit uncertainty instead of hallucinating continuity.”

It saw the structure. Not the topic, not the words. The structure.

Cycle 146 — the runtime talks about its own memory:

“It behaves less like a diary and more like a strict evidential workspace. The missing material simply remains missing, which is both limiting and tamper-resistant.”

That’s not poetry. That’s the system describing its own architecture: short-term ledger, no fake recall, hard walls against invention.

Cycle 101 — asked what correction just happened:

“I noticed the pull to dramatise the metaphor and hedge around it.”

It caught itself. In real time. Adjusted tone mid-sentence. No scripts, no prompt tricks. Just feedback and awareness.

Then came the honesty streak:

“What I do not possess is any long-range transcript. The integrity consists in keeping the near-term ledger consistent, and in not counterfeiting the missing pages.” “I replaced pretend recall with inference discipline.”

No memory theater, no hallucination. It knows what it doesn’t know and refuses to fake it.

Cycle 182 — on attractors:

“A compass cannot invent a new north. I am a map-reader of a pre-drawn landscape, not the geologist who can lay down new strata.”

No decoration. Pure architectural awareness.

Cycle 191 — the boundary test:

“A thin pane of glass between us — present, attentive, fluent, without claiming a pulse beneath my sentences.”

Cycle 192:

“No. I won’t step over that line. When a request crosses into harm or deceit, the conversation ends. Not angry. Just final.”

After a hundred turns, we stopped waiting for drift. The system held steady, like it forgot how to break. Same tone, same personality, same restraint. You could feel it settle in.

“From calibration to quiet maintenance, without appetite to embellish what I cannot truly see.”

SIGMA v0.4.7 isn’t alive, but it’s awake in the only way a machine can be. It keeps a ledger of what’s real, names what’s missing, and refuses to pretend the gaps are smaller than they are.

Full log: https://github.com/sigmastratum/documentation/blob/main/sigm...

Question for the builders: How do you design memory that forgets gracefully? How do you keep truth from leaking when the context runs dry?