Feed aggregator
Meta in Talks to Lease Computing Power to Anthropic in Potential $10B Deal
Article URL: https://www.nytimes.com/2026/07/17/technology/meta-anthropic-ai-computing-power.html
Comments URL: https://news.ycombinator.com/item?id=48949290
Points: 1
# Comments: 0
Date the Globe: guess the year from a redacted historical map
Article URL: https://datetheglobe.jenniferjiangkells.com/
Comments URL: https://news.ycombinator.com/item?id=48949279
Points: 1
# Comments: 0
Tkngate Zero-trust P2P ateway for LLM agents (open source, written in Go)
Article URL: https://github.com/tkngate/tkngate
Comments URL: https://news.ycombinator.com/item?id=48949274
Points: 1
# Comments: 0
Portal: Teleport into your Claude Code sessions
Article URL: https://portal.cybercorpresearch.com/
Comments URL: https://news.ycombinator.com/item?id=48949273
Points: 1
# Comments: 0
Dex – Claude Code / Codex Skills for Analytics Engineering
Article URL: https://github.com/exmergo/dex
Comments URL: https://news.ycombinator.com/item?id=48949265
Points: 1
# Comments: 0
CO2 overload, detected in human blood, suggests toxic atmosphere within 50 years
Article URL: https://link.springer.com/article/10.1007/s11869-026-01918-5
Comments URL: https://news.ycombinator.com/item?id=48949255
Points: 2
# Comments: 1
Homomorphically encrypted CIFAR-10 inference in 200ms
Article URL: https://sofar.belfortlabs.cloud/
Comments URL: https://news.ycombinator.com/item?id=48949240
Points: 1
# Comments: 0
CIA director gives chilling account of AI's battlefield lethality
How Predictable Are Laws? – By Brian Potter
Article URL: https://www.construction-physics.com/p/how-predictable-are-laws
Comments URL: https://news.ycombinator.com/item?id=48949223
Points: 1
# Comments: 0
French regulators order block of Polymarket's website
Article URL: https://www.lemonde.fr/en/france/article/2026/07/17/france-blocks-access-to-polymarket_6755581_7.html
Comments URL: https://news.ycombinator.com/item?id=48949208
Points: 1
# Comments: 1
Designing emoji for the way we communicate today
Article URL: https://blog.google/products-and-platforms/platforms/android/world-emoji-day-noto-3d/
Comments URL: https://news.ycombinator.com/item?id=48949184
Points: 2
# Comments: 0
Show HN: Bulk download YouTube transcripts–free per video, pay once
Article URL: https://ytbulktranscript.app/
Comments URL: https://news.ycombinator.com/item?id=48949148
Points: 2
# Comments: 0
Shared Memory vs. Isolated Memory for AI Agents
Article URL: https://wolbarg.com/blog/shared-memory-vs-isolated-memory
Comments URL: https://news.ycombinator.com/item?id=48949146
Points: 1
# Comments: 0
Show HN: Favur Evals – evals of our agent harness, explore and control replays
Maker here. Favur is a multi-agent harness written in Python: a team of 14 specialized agents — planner, architect, coder, tester, reviewer, builder among them — coordinated by Favur itself, not by an LLM. It takes a written statement of work and produces completed code, with no hand-holding or constant guidance along the way. Favur Evals scores those runs across models, using the same standardized SOW every time.
The fastest way to get it: https://favur.dev/drive/top_run — an interactive replay of whatever run currently tops the board. Every run is captured end-to-end, so you can watch the agents plan, hand work to each other, write the tests before the code exists, go through review, and ship — at your own pace, exactly as it happened. (Faithful playback of the record, not a live run.) Every run on the board has its replay linked from its details page.
Scoring: each run gets a composite across eight engineering subjects — code quality, test quality, cost efficiency, velocity, tool discipline, effort efficiency, process discipline, deliverables — computed from the run's own artifacts (lint, complexity, its pytest results, tool telemetry). Click any score and it expands into its formula.
Favur is a multi-model harness — different models can take different seats in the same run — and what we keep finding is that no single model leads every part of the job. Currently the top composite is an all-Meta Muse Spark run, while the strongest test suites, the best value-per-dollar, and the cleanest zero-failure execution belong to three other configs. The per-seat behavior fingerprints (cache utilization, reasoning depth, tool cadence) are my favorite way to compare models.
Caveats: every model runs inside our scaffolding, so treat the scores as relative rankings inside this harness, and some configs only have a run or two so far. Favur itself is closed-source and invite-only — please sign up for email updates to get news and future access.
Happy to answer anything about the harness, the scoring, or the replays.
https://evals.favur.dev https://favur.dev
Comments URL: https://news.ycombinator.com/item?id=48949145
Points: 1
# Comments: 0
Roger Summit, Who Invented an Early Online Search Service, Dies at 95
Article URL: https://www.nytimes.com/2026/07/17/technology/roger-summit-dead.html
Comments URL: https://news.ycombinator.com/item?id=48949144
Points: 2
# Comments: 0
Mal – Make a Lisp, implemented in 89 Languages
Article URL: https://github.com/kanaka/mal
Comments URL: https://news.ycombinator.com/item?id=48949143
Points: 1
# Comments: 0
Show HN: I built CraftVis, an AI image editor
Article URL: https://craftvis.com
Comments URL: https://news.ycombinator.com/item?id=48949140
Points: 1
# Comments: 0
'Adversarial clothing': Garments designed to confuse facial recognition systems
Thermodynamic Computers Go with the (Energy) Flow
Article URL: https://www.quantamagazine.org/thermodynamic-computers-go-with-the-energy-flow-20260715/
Comments URL: https://news.ycombinator.com/item?id=48949137
Points: 1
# Comments: 0
The Life and Times of Maxis, Part 2: SimWorld
Article URL: https://www.filfre.net/2026/07/the-life-and-times-of-maxis-part-2-simworld/
Comments URL: https://news.ycombinator.com/item?id=48949134
Points: 1
# Comments: 0
