Every agent can run a task. Almost none of them remember how they ran it last time.Nous Research shipped /learn for Hermes Agent on June 23. Feed it directories of code, API docs, manuals, PDFs, configs, past session logs, URLs - anything. Hermes distills the material into a SKILL.md file: a structured, verifiable, reusable skill it can call on in future sessions. No manual writing of the skill file required.The benchmark is concrete: agents with 20 or more self-created skills complete similar t
0:24
Every agent can run a task. Almost none of them remember how they ran it last time.Nous Research shipped /learn for Hermes Agent on June 23. Feed it directories of code, API docs, manuals, PDFs, configs, past session logs, URLs - anything. Hermes distills the material into a SKILL.md file: a structured, verifiable, reusable skill it can call on in future sessions. No manual writing of the skill file required.The benchmark is concrete: agents with 20 or more self-created skills complete similar t
x.comPrasenjit Sarkar已浏览 129.7万 次2 周前
Fable 5 is now available in Claude Code and CoworkFable is the best model I have used for coding, by a wide margin. It is a big step up, enabling less prompts and steers, more efficient token use, better code quality, better tool use, more intelligent self-verification, longer running sessions, and higher trust & autonomy. Happy coding!
0:20
Fable 5 is now available in Claude Code and CoworkFable is the best model I have used for coding, by a wide margin. It is a big step up, enabling less prompts and steers, more efficient token use, better code quality, better tool use, more intelligent self-verification, longer running sessions, and higher trust & autonomy. Happy coding!
x.comBoris Cherny已浏览 37.7万 次1 个月前
Taking a few vacation days to focus on the absolute insanity around https://t.co/JN7r9oC8c4.This started as another dumb weekend coding project and got WAY out of hand. I’m just a hardware guy who likes tinkering with weird new concepts, but this is starting to feel like OpenClaw 2.0.Going to speedrun the same loop: harden servers, fight fraud, onboard users, triage the flood of issues, cut deals, and try to keep the wheels on. Fight back the bot army, then focus on payouts. I’ll be live posting
0:24
Taking a few vacation days to focus on the absolute insanity around https://t.co/JN7r9oC8c4.This started as another dumb weekend coding project and got WAY out of hand. I’m just a hardware guy who likes tinkering with weird new concepts, but this is starting to feel like OpenClaw 2.0.Going to speedrun the same loop: harden servers, fight fraud, onboard users, triage the flood of issues, cut deals, and try to keep the wheels on. Fight back the bot army, then focus on payouts. I’ll be live posting
x.comAndrew McCalip已浏览 822.8万 次1 个月前
I love benchmarks like this because they show something people forget.There isn't one "best AI model."There's the best model for research.The best model for coding.The best model for creative work.The best model for cost.Fable seems to be pushing the ceiling on quality, while GPT 5.5 is making a very strong value argument.And honestly... users are the real winners here.
0:16
I love benchmarks like this because they show something people forget.There isn't one "best AI model."There's the best model for research.The best model for coding.The best model for creative work.The best model for cost.Fable seems to be pushing the ceiling on quality, while GPT 5.5 is making a very strong value argument.And honestly... users are the real winners here.
x.comSally Stockholm已浏览 236.5万 次1 周前
Claude Fable 5 is back — and live on RouterLink 🔥The model that broke the coding benchmarks is production-ready again.One API key. Every frontier model. Day one, every time 🔗#WORLD3 #WAI #AIagent #RouterLink
0:13
Claude Fable 5 is back — and live on RouterLink 🔥The model that broke the coding benchmarks is production-ready again.One API key. Every frontier model. Day one, every time 🔗#WORLD3 #WAI #AIagent #RouterLink
x.comWORLD3已浏览 1652.8万 次1 周前
The AI war right now is about what gets embedded into the daily work of a company. It's similar to the 1990s. Windows and Office became the working environment of business. Alternatives existed, but most companies used Microsoft products because that's how you got work done.That is the real story behind this chart.Anthropic has overtaken OpenAI in corporate AI, in terms of US businesses making paid transactions with each AI supplier. Once an AI tool becomes part of how work is actually done, it
0:30
The AI war right now is about what gets embedded into the daily work of a company. It's similar to the 1990s. Windows and Office became the working environment of business. Alternatives existed, but most companies used Microsoft products because that's how you got work done.That is the real story behind this chart.Anthropic has overtaken OpenAI in corporate AI, in terms of US businesses making paid transactions with each AI supplier. Once an AI tool becomes part of how work is actually done, it
x.comJames Eagle已浏览 19.3万 次3 周前
🚨 Anthropic's CEO:"In the next 3 to 6 months, AI will write 90% of the code, and within 12 months, nearly all code may be generated by AI."so the job isn't coding anymore.it's not hiring either.it's building. building systems that run without you.no hires. no overhead. no bottleneck.One person. Claude Cowork. A fully operational business. here's exactly how to build it ↓
0:32
🚨 Anthropic's CEO:"In the next 3 to 6 months, AI will write 90% of the code, and within 12 months, nearly all code may be generated by AI."so the job isn't coding anymore.it's not hiring either.it's building. building systems that run without you.no hires. no overhead. no bottleneck.One person. Claude Cowork. A fully operational business. here's exactly how to build it ↓
x.comRahul已浏览 6.9万 次2 周前
1:48
I'm leaving coding behind me, Bjarne is fully right about AI and if you want performance on the backend you should stick with the manual art of coding.Management needs AI to be in every slide, so in the coming few years there the focus will be all into AI.As a senior my brain refuses to validate AI output, it's way worse than guiding a junior in the team.So my time in tech will end this year, and I'm not sure what my next step will be.
x.comMario Verbelen已浏览 174.7万 次1 个月前
1:21
Three skills I use every day in Claude Code and Codex to solve my hardest problems:1️⃣ /agent-watchdogWhen I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread.You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and autom
x.comSteve (Builder.io)已浏览 3.1万 次3 周前
0:30
Anyone watching recursively self-improving agents knows how good they've gotten at optimising over a fixed benchmark with verifiable rewards, like math or coding. Our recent work, the Red Queen Gödel Machine (RQGM), co-evolves the evaluation itself together with the agent. 🧵
x.comAlex Iacob已浏览 8161 次1 周前
0:25
AI coding agents have access to your API keys, your codebase, your production environment. One prompt injection and they work for someone else. Gate AI sits inline on every request and stops it. Launching June 2026.
x.comConstellation²已浏览 1213.6万 次1 个月前
1:46
Fully Aggressive variant Uncensored MoE model that won’t refuse red team or pentesting tasks & coding.- 35B parameters, 3B active (MoE)- 0 refusals (Aggressive variant)- Excellent agentic coding + multimodalPowerful uncensored coding model 73.4% on SWE-bench Verified & fully uncensored, It dangerous (in a good way).This is currently one of the best options if you want power without guardrails.High quality imatrix GGUF quants available
x.comMd Ismail Šojal 🕷️已浏览 4419 次1 周前
0:15
STANFORD JUST BUILT GIT FOR LIVE AI AGENTSthey call it Shepherd and it lets you rewind a running agent to any earlier step and pick up from the exact statewhen an agent works a long task the run piles up state, edited files, a dev server, a database, installed packages, a warm KV cachesay it's on step 10 and misreads a traceback, then rewrites a file that was actually finetests start failing and the whole run drifts, even though steps 1 through 8 were perfectnormally the agent just tries to patc
x.comAtlas已浏览 4147 次1 周前
0:10
Everyone is arguing about which AI coding agent is best.GitHub just showed that they've all been asking the wrong question.95K+ stars.8K+ forks.In just a few days.Not for a new AI model.Not for another coding agent.For a workflow.Here's the mistake almost everyone makes:Open Claude Code.Open Cursor.Type:> "Build me a SaaS."The AI immediately starts writing code.It makes assumptions.Adds features you never wanted.Misses edge cases.Then you spend hours fixing AI-generated code.The problem wasn't t
x.comShruti Codes已浏览 1481 次2 周前
0:16
Fastest Growing Startup in EU History
YouTubeJoe Rorgan Podcast Clips7 个月之前
Top 10 Coding Platforms to Enhance Your Coding Skills in 2025 - GeeksforGeeks
geeksforgeeks.org2020年2月29日
Arithmetic coding for data compression | Communications of the ACM
acm.org2019年12月29日
Coding, Decoding, and Reasoning: Questions Tricks & More | Simplilearn
simplilearn.com5 个月之前
展开
静态缩略图占位符