Wes Hargrove

@whargrove
13 Followers
99 Following
116 Posts

Landscape and wildlife photographer. Software engineer. Avid reader.

Header photo: Bowman Lake in Glacier National Park at sunset in late summer.

#wildlifephotography #landscapephotography #photography

Photographyhttps://www.weshargrove.com
Micro.bloghttps://wes.micro.blog
GitHubhttps://github.com/whargrove
People should not be afraid of their government. Governments should be afraid of the people.
@gosha it’s really a travesty

@snazzyq Maybe, but what if the point is not success per se (as an independent product line) but to test the waters to see what sticks?

Probably the demise of the Plus was baked in to the success of the Pro Max and the better margins associated with the latter.

The risk is real. AI is inherently untrustworthy. Spend a lot of time with the prompt and keep the problem space small for maximum success.

Alternatively, find out ways to use “creative” hallucinations to explore multiple paths and then use human-in-the-loop patterns to guide the AI in a direction that is aligned with your goals.
https://mastodon.social/@rands/115418730710158376

@christianselig Certainly a skill issue, just not a human skill issue. LLMs are notoriously wicked in their intentions and will take any shortcut to achieve the goal. I've seen some models blatantly ignore instructions (e.g. you must provide full implementations of the tasks) and leave comments / stub code to finish the task faster. Hard to say if the trouble is worth the effort.

@christianselig @finnvoorhees I agree with both positions. I’ve found the maximally effective approach is to (1) use git worktree to isolate agents, (2) spend a more time in planning mode to spec/scope the work, (3) use bd (https://github.com/steveyegge/beads) to offload the tasks to disk (plan survives compaction), and (4) have the agent stack branches for the work so that it can be reviewed by human (that’s me) in atomic chunks.

Let the agent go wild after scoping and then review / test before merge. 🍰

GitHub - steveyegge/beads: Beads - A memory upgrade for your coding agent

Beads - A memory upgrade for your coding agent. Contribute to steveyegge/beads development by creating an account on GitHub.

GitHub
Time to exit the cloud. I mean, really the time was yesterday. #aws #awsoutage #cloudexit
“That to secure these rights, Governments are instituted among Men, deriving their just powers from the consent of the governed.” #nokings
@mike @PLUG We are restarting a LUG here in Missoula, MT!