Bummer, am talking about Hermes with the CTO of @NousResearch then. Will join after if you are till running.
CODE
-
Web Scraping vs API Compliance for AI News Aggregation
By
–
Scraping is against X's Terms of Service. How do you get around that? I guess it's OK for personal use, since X can't tell you are scraping, but if you build a public site, like mine: https://
alignednews.com/ai which uses the X API, then I can't scrape, but have to be legit. -
Guided vulnerability detection differs from autonomous discovery
By
–
It's very cool work, but it's not 1:1. The report shows that they basically lead the models to the right spot for them to do the work. It's more "is this a vulnerability?" than "find a vulnerability". Mythos had to find it from scratch, these were told where it was.
-
Neurosymbolic AI Vindication: Beyond Pure Language Models
By
–
it’s surely NOT a pure LLM (eg heavily uses symbolic tools and is hardcoded to do so), and surely includes neurosymbolic components, so it is to some degree vindication for my central claims.
-
SF Meetup: Building Better Agents with Improvement Loops
By
–
🌉 Join us in SF for a meetup on building better agents with the agent and code improvement loops. You'll hear talks by @samecrowder, Head of Product at @LangChain, and @nnennahacks, AI Developer Relations Lead at @QodoAI .
— LangChain (@LangChain) 8 avril 2026
Sam will walk through the agent improvement loop and… pic.twitter.com/9e61dYvueD🌉 Join us in SF for a meetup on building better agents with the agent and code improvement loops. You'll hear talks by @samecrowder, Head of Product at @LangChain, and @nnennahacks, AI Developer Relations Lead at @QodoAI . Sam will walk through the agent improvement loop and how teams use traces as the foundation for continuous improvement. Nnenna will present how Qodo is building agents, their architecture, and how they’re enhancing them using LangSmith. 🗓️ Wed, April 29 | ⌚ 6 PM | 📍 SF (SOMA) RSVP 👉 luma.com/4nu6vpsh
-
7 Pillars of Agentic AI by Python Developer
By
–
7 Pillars of #AgenticAI
— Ronald van Loon (@Ronald_vanLoon) 8 avril 2026
by @Python_Dv
#LLM #GenerativeAI #ArtificialIntelligence #MI #MachineLearning pic.twitter.com/dGCIxouNTT7 Pillars of #AgenticAI by @Python_Dv #LLM #GenerativeAI #ArtificialIntelligence #MI #MachineLearning
-
Open Source Software Update Practices and Community Standards
By
–
Similar issue here. Pretty much everyone in the field had similar concerns; anyone with substantial open source software had a mailing list; software updates generally followed a common format.
-
Critical Analysis of AI Safety Verification Tools and Benchmarking
By
–
link to @HeidyKhlaaf’s sharp analysis: Dr Heidy Khlaaf (هايدي خلاف) (@HeidyKhlaaf) As someone who has audited dozens of safety-critical systems, built static analysis tools, and used most formal verification and security tools, here are some red flags that should be a caution in taking these claims at face value: 1. There are no comparison benchmarks with 1/ — https://nitter.net/HeidyKhlaaf/status/2041591737563394442#m
-
Cursor’s AI Code Review Agent Learns From PR Activity
By
–
Cursor's code review agent can now learn from activity on PRs to self-improve in real time. 78% of issues found are resolved by the time the PR is merged.
-
Meta’s Muse Spark: Multimodal AI with Strong Reasoning and Coding
By
–
Muse Spark, the first model from meta superintellgence lab looks very good, with strong multimodal, reasoning, and coding capabilities, although it is closed source for now. don't be angry with me for the headline @finkd
!