William Hallatt

Here for the tech and the thinkers. 'front left' is about leadership and AI-first product teams.

[William Hallatt @frontleftwill]

@harleyf Ye Olde Conscientiousness Factor

[William Hallatt @frontleftwill]

@staysaasy @harleyf You can get a very good sense for it by moving away from overly structured interviews to more conversational styles, with the caveat that you need to learn how to use open questions to probe intrinsic motivation effectively.

[Harley Finkelstein @harleyf]

The most underrated hiring signal:
the Give-a-Shit Quotient.

[William Hallatt @frontleftwill]

@karrisaarinen The client benefits from better products, and the model providers benefit as the platform providers who are enabling the productivity competition - you and your competitor are both 10x more productive, why would the client pay more for either product in a free market economy?

[Uncle Bob Martin @unclebobmartin]

I am absolutely more productive using agents. I don't know the factor but it's large. However much of that productivity is spent tuning the agents and hardening the product. I'm guessing 30%-40%.

Some might consider that a waste; but I don't. The software I'm creating nowadays is vastly more robust than I'd ever been able to create manually.

I don't mean that the code is better. I mean the surrounding tests are vastly better. I have a higher degree of confidence than I ever had manually -- even when I used very disciplined TDD and Acceptance testing.

And then there's the ability to quickly reorganize the modules and the architecture while keeping those robust tests running. That is a tremendous boon.

[Raspberry Pi @Raspberry_Pi]

"My most daily used agent is running off a Raspberry Pi which is at least two or three years old; all that it has is 8GB of RAM. You see my point about accessibility, personalisation, relevance, use. [...] This is my point: the barriers have fallen." 🫶

Singapore's Minister for Foreign Affairs, Dr Vivian Balakrishnan, built his own agentic AI tool running on a Raspberry Pi (inc appropriate security measures!)

[ITER @iterorg]

ITER marked the start of operations at its MCTF — building knowledge, infrastructure, and operating experience for the wider fusion ecosystem. After the first coil cooldown to 4 K, the facility will support magnet testing ahead of installation. https://t.co/QIjg8QLdRb

[David Cramer @zeeg]

I guess people dont read between the lines, but:

1. 1:1s are fine, weekly are not. Except in specific scenarios like new employees, pips
2. 1:1s are not "the mechanism to communicate with your team"
3. group sessions should replace most activities happening in weekly 1:1s

[Sabine Hossenfelder @skdh]

it's funny because it's true 🤣

[kepano @kepano]

engagement-bait accounts love to weaponize Cunningham’s law:

"the best way to get the right answer on the internet is to post the wrong answer"

it's a lose-lose for the target because if you don't reply it allows misinformation to spread, if you do reply it boosts the post

[tobi lutke @tobi]

So good

[aaron @aarondotdev]

feels like AI is 10xing too many -1x developers

[Teknium 🪽 @Teknium]

Introducing Hermes Curator!

The new system built in to Hermes Agent now helps you keep your skills that the self improvement loop creates in check, by consolidating and pruning automatically.

The curator does multiple things:

- keeps track of how often you use each skill, when it was last updated/created, etc

- Once a week runs automatically (configurable)

- Uses the analytics plus it's own scanning of your skills and consolidates or prunes them if necessary

- Skips externally installed skills, built in skills, and skills you "pin" that you dont' want touched. It will only attempt curation over agent created/updated skills or user written skills.

- It will then determine whether skills can be consolidated, pruned, or otherwise made more manageable. It will convert some skills that are too specific into references, templates or scripts for larger/broader skills, or integrate them directly into a consolidation of an existing skill.

You can also disable it entirely in the config.yaml and/or run it manually with `hermes curator run `

Learn more on the docs here:

https://t.co/6woLLRtDLP

[Nous Research @NousResearch]

Hermes Agent v0.9.0 - “The Everywhere Release”

Full changelog below ↓

[William Hallatt @frontleftwill]

@browser_use @NousResearch Sign up with GitHub fails.

[William Hallatt @frontleftwill]

@bcherny I read that as "NO_FUCKER mode" and now I feel a bit let down if I'm honest 😆

[William Hallatt @frontleftwill]

@qwertee your contact form returns an "Internal Server Error"

[tobi lutke @tobi]

The essence of engineering is to get the most out of the system given the constraints. Sometimes thats runtime performance, sometimes thats speed. The best can get the sweet spot between both. They are not children that need chocolate treats for doing their work well. They have professional pride to do great work. And then make more money through promotion and raises which last the career rather than a one time thing.

[Gergely Orosz @GergelyOrosz]

If you use GitHub (especially if you pay for it!!) consider doing this *immediately*

Settings -> Privacy -> Disallow GitHub to train their models on your code.

GitHub opted *everyone* into training. No matter if you pay for the service (like I do). WTH

https://t.co/vcSkhM5yLV

[Daniel Hnyk @hnykda]

LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server + self-replicate. link below