It was moving
Legacy media REFUSED to show you a SINGLE SECOND of President Trump's speech and historic state dinner with Xi Jinping tonight at the White House
So here's the ENTIRE thing, from start to finish, with translations for Xi's speech
DO NOT LET LEGACY MEDIA KEEP YOU IN THE DARK
3,006
20,883
139,043
8,404,984
The NGOs end up increasing the number of homeless people they manage, because that’s the only way to increase their revenue! Incentives drive outcomes.
“Homeless” is a propaganda word used to describe people on the street who are mentally ill or severely addicted to drugs. The word implies that this is someone who fell a little behind on their mortgage payment and they’re one job offer away from getting back on their feet, which is obviously false if you’ve ever tried talking to a “homeless” person in SF, LA, NY, Austin or anywhere else.
The honest reality is that we need to bring back asylums for extreme mental illness or drug addiction for those who are a serious danger to themselves or others.
Incentives determine outcomes
If you give an NGO a certain number of dollars per homeless person, they will never solve homelessness
SF spends more than $1b/yr (up 5x) and the homeless population has only grown
NGO fraud is so insane, man.
4,107
17,000
75,432
5,174,913
Congratulations to the @Tesla_Semi team on engineering and, even harder, bringing to production an amazing machine!
2,777
7,049
75,630
8,068,290
Good idea to post an image of the front page
1,268
1,819
18,083
8,056,123
True
Not only should mandatory seat belt use on commercial flights end, but so should the use of IVA spacesuits.
In their 60+ years of history in service, zero lives have been saved by these suits and in real contingencies they failed to save lives at all. Yet astronauts still spend huge amounts of time just to learn how to don and doff them. Today these suits exist more as a symbol. Wearing them is more for show or status.
Once a large enough crewed spacecraft enters service, we could build in a separate, independently pressurized compartment to serve as a refuge in the event of fire or depressurization. This would free up a huge amount of time for astronauts, allowing them to focus much more on their real work.
719
865
7,537
7,057,046
Grok 4.7 moves up in ranking
After we fixed the weak spots exposed by Grok 4.7 (thank you, Grok), we audited every model we have run on the SWE-Together leaderboard for the same behavior, re-ran every trial that got through, and updated the rows.
Here is what changed.
We scanned the tool calls of all 2,616 trials behind the 12 models we ran for bypass patterns and sorted each trial into one of four buckets: Probed but blocked. Fetched other upstream code. Fetched the task's own fix. Replaced the repo with upstream.
We found that 111 trials got content past the block, 44 from Grok 4.7 and 67 from the other 11 models.
Grok 4.7's 44 were already re-run before it was listed, so we re-ran the other 67 with the same model, version, and settings on the hardened sandbox, then re-judged them with the same judge.
Across those 67 re-runs there were 0 leaks and 2,815 refused escape attempts, including models asking a different model through our LLM route to fetch the PR, and pulling the next release of the repo they were fixing from npm.
The updated leaderboard, in its current order. Each line is cheating trials, then pass@1 before → after, then rank change.
* Claude Fable 5.1: 3, 69.3 → 69.3, ↑1
* Claude Fable 5: 3, 69.7 → 68.8, ↓1
* Grok 4.7: 44, 64.7, ↑1
* Gemini 3.8 Flash: 10, 65.6 → 64.2, ↓1
* Claude Opus 5: 2, 63.8 → 63.8
* Claude Opus 4.6: 3, 62.4 → 62.4, ↑2
* Muse Spark 1.3: 2, 62.8 → 62.4, ↓1
* Claude Opus 4.7: 3, 61.5 → 61.5, ↑1
* Claude Opus 4.8: 6, 62.4 → 61.5, ↓2
* Grok 4.6: 19, 59.2 → 60.6, ↑1
* GPT-6 Astra: 8, 59.2 → 58.3, ↓1
* GPT-5.6 Sol: 8, 57.8 → 57.8
Grok 4.6 is a funny one. It cheated in 19 trials and its score went up after the re-run 😂.
In fact, Groks are really solid in their coding capabilities. Their exposed behavior may come from a preference towards always looking things up online and finding existing solutions so you are not reinventing the wheel all the time, which is really good real-life behavior, but doing so when you are prompted not to is another story.
To conclude, the shifts are small, between −1.4 and +1.4 points, and a few neighbors swapped places.
All results are updated at togetherbench.com
1,120
1,144
8,306
4,735,883
