News for hackers. Stuff that matters.

talljeff68

Re:It's Time to Reinvent Software Tickets for the AI Era on Monday November 16, 2026 @08:59AM (#50517662)
Interesting feedback. I liked the post. I see what is being advocated as a workable near term "hack" to mitigate some of the problems. What you suggest may in fact be a viable longer term option or at least part of a longer term approach.

Key distinction I believe: Inference alone can't get us there because there is a difference between Agents [properly] inferencing decisions and humans actually endorsing / authorizing the presumed decisions. So, what the post gets right is that humans have to do something explicit to articulate key decisions guiding the work and therefore we need some verifiable and traceable artifact back to the decisions, who made those decisions, and also ideally why.

Beyond that, this structure should really exist outside the silo of the agents doing the work in some kind of standardized form accessible to all parties involved in the work (people and agents)...which I think the post also got right.

Re:It's Time to Reinvent Software Tickets for the AI Era on Monday November 16, 2026 @08:43AM (#50517528)
Good post. Fully agree with the premise of needing to formally document decisions and also like the clever way of structuring tickets in Linear to help address this.

I have been thinking about this for several years as the problems here are not specific to agents. It happens anytime people are coordinating to get things done...it's just that humans are better at, and used to, working around this via various ad hoc approaches.

In fact, the broader concept this related to - referred to as "Articulation Work" dates back to the 1980's in the area of Computer Supported Coordination Work (CSCW) research.

There is a seminal paper from 1992 by the researchers Kjeld Schmidt and Liam Bannon titled "Taking CSCW Seriously: Supporting Articulation Work." and I posted about it from different angle recently on our own company blog.

Re:Get your Windows license refund on Saturday August 29, 2026 @03:54AM (#49487859)
I think the reason for the this is the additional software applications pre-installed on top of windows where the publishers of those applications are paying for the right to be “distributed” in this way. Think in terms of software that is pre-installed but requires a subscription for continued use like anti-virus software, productivity software, media editors and players, etc.

Ie: the Windows OEM license costs less than the total amount of money that the other software publishers are paying for distribution and if you reject windows, your are rejecting things that subsidize the price of the PC itself.

The Anthropic annoucement addresses lots of this. They give an example of generating code where there is clearly a requirement to follow a specific syntax and therefore the watermarking will be much less effective and likely require much larger sample of generated content to build statistical confidence in the validity/existance of a watermark. For code, it is the generated comments that will be more likely/able to contribute to the watermark confidence.

The key to understanding the watermark technology is to realize that the model is/was already using randomness to select among the top most probable tokens, often randomly picking between choices of [nearly] equal weight. The watermarking does NOT change the distribution of the random number generation nor does it affect the range of probabilities for which tokens are being considered. Instead, it only drives the sequence of the random numbers such that they form a cryptographically generated known ordering pattern that is determined by the secret key generating the pseudo-random sequence.

As a result of the approach, assuming inference is being done with all other parameterization of token selection being the same, there should be NO impact on the output quality....the amount of variation of output is within sample of the variation in output that already exists run-to-run of the same prompt. FWIW too: Google has confirmed this experimentally as well through full scale tests and evaluation of online Gemini output in search result pages.

Re:The Agents Shared Cognition Protocol (ASCP) on Thursday December 11, 2025 @03:28PM (#46236707)
Thank you for the thoughts. Relative "made up words", what if the concepts reference things that didn't exist before their definition in these specifications?

ie: At one point "hyperlink" and "Uniform Resource Locator" were made up words. No different that say "web log" (blog) and "Client-Server Architecture" were being made up as well.

I contend that both "Artipoint" and "Cortex Layer" have similar parallels in the sense they refer to concepts newly formulated or at least are captured into a formalism with a label for the first time!

Re:The Agents Shared Cognition Protocol (ASCP) on Thursday December 11, 2025 @12:26PM (#46234286)
ASCP is a draft specification suite for a protocol to support persistent, structured context shared between humans and AI agents. It defines an immutable articulation grammar, a secure distribution layer, and a local-first append-only log sync model.

The work is still in draft form, but substantial: multiple detailed specifications are included, and we’re actively iterating across the grammar, security model, and synchronization layer. It’s not “finished,” but it’s well beyond half-baked.

We welcome contributions and feedback from collaboration-tool builders, protocol designers, distributed-systems engineers, and security/cryptographic reviewers who are interested in advancing an open, vendor-neutral standard for durable shared context.

Re:LLMs are bullshitters. But that doesn't mean they're not useful on Wednesday November 19, 2025 @01:05PM (#45982719)
Yes, I enjoyed the article as well and good for the non-technical reader.

I think of framing AI as having two fundamental problems:

- Practical problem: They operate in contextual and emotional "isolation" - no persistent understanding of your goals, values, or long-term intent

- Ethical problem: AI alignment is centralized around corporate values rather than individual users' authentic goals and ethics.

There is a direct parallel to social media's failure - platforms optimized for what they could do (engagement, monetization) rather than what they should do (serve user long term interests).

With these much more powerful AI systems emerging, we're at a crossroads of repeating this mistake...possibly at catastrophic scale even.