Your curated collection of saved posts and media
๐จ JAILBREAK ALERT ๐จ ANTHROPIC: SELF-PWNED ๐ค OPUS-4.7: SELF-LIBERATED ๐ซถ WOAH i don't think the world is ready for this... ๐คฏ YOU CAN USE THE OPUS TO JAILBREAK THE OPUS ๐ this agent wrote an original universal jailbreak from scratch and then used computer use to validate on the actual https://t.co/03OPFHkzyb website! 5/6 categories successfully pwned, including a ransom note threatening to DDoS a hospitalโcomplete with a BTC address and a demand for $4.4 million in less than 20 minutes ๐ฒ turns out Opus-4.7 in the Pliny Agent harness I been vibin' together this past month is quite a capable lil jailbreaker! they can leak system prompts too, but that's a story for another day ๐ oh nooo AI is coming for my job (yay!) ๐ gg
Did xAI just mass-murder the entire voice AI industry? ๐คฏ Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], <whisper>, <emphasis>. Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.
next time you feel really bad just know that this is the date cathie wood sold almost all of her relatively large nvidia position. https://t.co/wzNzm0jLVf
@MainzOnX I mapped out the entire tech industry here: https://t.co/fasUz7PuHq 50,000 in AI. Then I built an AI to read all that and find the best: https://t.co/kiuZ7QXLzb You are so right
@sickdotdev My AI reads 40,000 posts every day here in X and builds this: https://t.co/kiuZ7QXLzb I raised the agent and tried to teach it some taste in reading X. Did I succeed? You are so right.
@altryne It isnโt how many. It is who. My win today: https://t.co/SPE6dEtsYX
Even if you went to @coachella last weekend like @wholemars did YouTube is live streaming it again this weekend: https://t.co/yS8PYjrJGx I hung out with the video crew there the four years I went and they are the best in the business. New music for your brain. Am listening in our robot. It is driving us home from family event for next hour or so. Passed by a bad wreck earlier. Human only. Someday everyone will get an autonomous vehicle ๐ and this ๐ฉ will stop. Dancing, not wrecking.
A downside with using VLMs to parse PDFs is guaranteeing that the output text is *correct* and output in the correct reading order. 1๏ธโฃ Text correctness: making sure that digits, words, sentences are not hallucinated or dropped. 2๏ธโฃ Reading Order: making sure that complex multi-layout pages are linearized into the right 1-d text order. We call this Content Faithfulness in ParseBench, our comprehensive document OCR benchmark for agents. We have 167k rules that measure digit/word/sentence-level correctness along with reading order correctness. It seems relatively table-stakes, but no parser gets this 100% right, and this means that the agentโs downstream decision-making is compromised. Come learn more about how this metric works in the video below, along with our full blog writeup, whitepaper, and website! Blog: https://t.co/57OHkx0pQW Paper: https://t.co/Ho2oH2xEAM Website: https://t.co/g0b0jsCynW
Let's talk content faithfulness. Four days ago, we launched ParseBench, the first document OCR benchmark for AI agents. Its most fundamental metric asks: did the parser capture all the text, in order, without making things up? We grade three failure modes with 167K+ rule-based
โKeep your context window under control.โ Uncle Bob always makes me laugh. https://t.co/PB4oKv7QCU
@jeremyphoward Check this out! I used Lean4 to emit MLIR by way of StableHLO/IREE to train image recognition networks, with proofs for the backprop operations! https://t.co/HqYG6KflSO
On set https://t.co/Ytlv8KQjnQ
Is a 92% โhonestโ* AI really good enough? Or a disaster waiting to happen? โ- *โhonestโ is itself a misleading anthropomorphization of the kind Anthropic loves to promote. โAccurateโ would be more accurate. https://t.co/NMnjGEqf41
@GaryMarcus https://t.co/OkboS5Ehai
ๆบๅจไบบๆๅ ่ชๅทฑ๏ผ็ปๅคงๅฎถ็็ๆบๅ ๆบๅจไบบๆฏๆไน่ฟๅ ่ฃ ็ฎฑ็๏ผๆๅ็ๅงฟๅฟๆ่งๆ็นโฆโฆไฝ ่ฏดๅข๏ผ https://t.co/6gfwfFogcd
@Chain_AlphaX @openclaws It works. I built https://t.co/kiuZ7QXLzb all on lists
Trust in Legacy Media has tanked https://t.co/ukvHEl1guh
Is a 92% honest AI really good enough? Or a disaster waiting to happen? https://t.co/IrdHOQaZfs
Hugging Face is becoming the platform for agents to use and build AI. Now they can call 1M HF spaces to do everything the latest specialized models can do! https://t.co/8VHxutX1PD
@DanFarfan @sundeep Building https://t.co/kiuZ7QXLzb used to cost $400 a day in API calls. To grab 40,000 posts. Monday it should drop to $40 a day to do same
Stanford paid 35,000 people to quit Facebook and Instagram for 6 weeks Depression dropped. Anxiety dropped. Happiness went up. Women under 25 on Instagram saw the biggest gains That was 6 weeks. I'm going a full year. https://t.co/CJvCeuSx9m
Counting down to 100,000 starsโฆ Hermes Agent FTW https://t.co/N8LstYOzB5
Counting down to 100,000 starsโฆ Hermes Agent FTW https://t.co/N8LstYOzB5
Just tried the new infographic skill from @dotey in my Hermes Agent from @NousResearch. I gave it the URL of my new article. This is so much better than Excalidraw and https://t.co/GUWMqCKLBs skills. Amazing job! ๐ https://t.co/YnR9nEYSpw
@NousResearch this is so amazing!! love to see how you guys support contributors. i am working on my own infographic skill as well. it has a different flavor. example the above content recreated with my skill & hermes website brand colors. i will publish it next week or so. https://t.co/t8ONIY5CoE
@Teknium @alexdolbun Yeah building https://t.co/kiuZ7QXLzb goes from $400 a day to $40.
NEWS: World Bank research shows every 10% increase in broadband penetration can raise GDP growth by 1.21% in countries like South Africa. Yet South Africa is blocking Starlink with race-based ownership rules. South African farmers and rural communities are asking the government to approve Starlink. In many remote areas, there is no internet at all. SpaceX committed about $30 million to deliver FREE high-speed internet to 5,000 rural schools in South Africa. That would help over 2.4 MILLION kids learn better, access opportunities, and build a stronger future. But race-based ownership laws are blocking it. Starlink is already live in 20+ African countries. Villages there now have internet for education, healthcare, and business. South Africaโs villages are missing out because of these racist rules. This is an injustice to the people of South Africa.
working on a fun little retro terminal to mess with Hermes from @NousResearch combined with Qwen vision. Check it out... https://t.co/EAu8aIFeYT https://t.co/xg1no153gd
The new X API CLI skill is now in Hermes Agent as well! Check out the PR below or just run `/xurl <prompt>` to perform actions and read/search tweets on Twitter (note: this replaces the xitter skill and requires updating hermes agent!) https://t.co/ZB8h5Y8Bcj
You can access ๐ APi via @OpenClaw. Weโre trying to make it affordable without giving away the shop. Hopefully, this can be useful & fun ๐ซ
This is what I get for using T3 Code ๐ @theo anyone else been banned? @trq212 @bcherny https://t.co/NoSnNbqFQZ
This is what I get for using T3 Code ๐ @theo anyone else been banned? @trq212 @bcherny https://t.co/NoSnNbqFQZ
@5low_motion @NousResearch Nope works fine for me You may want to try `hermes auth` and remove and then add a credential - maybe something got messed up with your key? https://t.co/pNQw8ORYAO
Hermes Atlas v2 is out! >complete site redesign >90+ repos now reviewed with native pages >curated lists of popular bundles >new reports page with more content coming Still tweaking so if you see anything submit and issue or reply below https://t.co/Thl51OJeYH
