HNHacker News
TopNewBestAskShowJobs

Bnjoroge

322 karma · joined April 13, 2020

submissionscomments
Bnjoroge··on Claude Opus 4.8
Have you seen https://deepswe.datacurve.ai/blog? This is the closest to a vibe check i’ve felt even with the open models.
Bnjoroge··on Claude Opus 4.8
For long-running tasks, yes 4.7 has been a noticeable improvement. Goes off the rails alot less than 4.6 does. For shorter-sized windows, I havent felt as much and agree that the harness improvements have been fhe biggest lever
Bnjoroge··on Outsourcing plus local AI will soon become more economical vs. frontier labs
I imagine it’s also really trivial to build some kind of local “enterprise” proxy that gives you the same visibility in usage as the anthropic dashboard would give you. I use one for aggregating all my subs.
Bnjoroge··on Why AI Agents Cannot Change Software Systems
Yup. Just shows me that they are either oblivious about how much better they’ve gotten or simply unaware. Either way, hard to take their opinions seriously
Bnjoroge··on GitHub Actions was down
Gitlab’s UI is extremely terrible. It’s hard to even explain how bad it is.
Bnjoroge··on Bun support is now limited and deprecated
Do you review your dependencies’ entire code?
Bnjoroge··on Bun support is now limited and deprecated
There’s a big difference between vibe coding and agentic engineering. If you think they are at all the same thing, you need to update your priors
Bnjoroge··on OpenAI Is Preparing to File for an IPO Soon
I dont think that holds since the core cuda toolkit is proprietary
Bnjoroge··on OpenAI Is Preparing to File for an IPO Soon
You only need about a mac w 96GB or 128gb to run deepseek v4flash with ds4(https://github.com/antirez/ds4). Works mostly well
Bnjoroge··on AI subscriptions are a ticking time bomb for enterprise
Subs are absolutely available to businesses. There’s metered plans for ghe equivalent consumer plan.
Bnjoroge··on US special forces soldier arrested after allegedly winning $400k on Maduro raid
whoops yea, my bad.
Bnjoroge··on US special forces soldier arrested after allegedly winning $400k on Maduro raid
It is not difficult to believe that the frustration of racist people seeing black people more successful contributed to it. In fact, it's the most obvious and straightforward explanation for it, given the fact that it's 1)1921, 4 or so decades before the Civil Rights act, and in freaking TULSA lmao
Bnjoroge··on US special forces soldier arrested after allegedly winning $400k on Maduro raid
you are incredibly naive, ignorant or oblivious if you dont think a primary reason was because of their race in TULSA in 1921. Cmon man -read some history
Bnjoroge··on US special forces soldier arrested after allegedly winning $400k on Maduro raid
honestly the entire country up until maybe 40 or so years ago
Bnjoroge··on Show HN: Agent Vault – Open-source credential proxy and vault for agents
infisical is great so excited to see this
Bnjoroge··on Atlassian enables default data collection to train AI
I believe you have to disable the toggle, but not sure if it applies to folks who dont use copilot: https://github.com/orgs/community/discussions/188488
Bnjoroge··on Atlassian enables default data collection to train AI
Plenty of other companies enable this by default too, such as Github, Figma, Adobe, Vercel. I think it's fair to assume that if you ahve data stored within any company, they'll by default use it for training.
Bnjoroge··on We've raised $17M to build what comes after Git
you just need pedigree. any kind. where you went to school, where you worked etc.
Bnjoroge··on Launch HN: Freestyle – Sandboxes for Coding Agents
Looks cool - would be great to see a PR with some benchmarks on this repo if you can: https://github.com/computesdk/benchmarks

edit: just saw the pr for freestyle. something seems to be blocking, but curious how it compares: https://github.com/computesdk/benchmarks/pull/41

Bnjoroge··on Artemis II crew see first glimpse of far side of Moon [video]
that's absolutely not what he said lmao. he said it's far down on our list of priorities, which is true.
Bnjoroge··on Artemis II crew see first glimpse of far side of Moon [video]
there's zero difference between a photo taken by them and one by cameras on ISS.
Bnjoroge··on Artemis II crew see first glimpse of far side of Moon [video]
the hell does that have to do with anything
Bnjoroge··on Show HN: ctx – an Agentic Development Environment (ADE)
> it's instructed to understand both sides before resolving. This is the crux of the issue. You are delegating the resolution of conflicts to an agent, which is fine, but doesnt solve the core issue that there's no scalable way to actually do this. It is far from a solved problem lol, just because your agents havent had issues resolving them.
Bnjoroge··on Show HN: ctx – an Agentic Development Environment (ADE)
Looks cool! Two things: I see you mentioned the merge queue, but how exactly do people avoid or resolve merge conflicts when merging work from two or more agents in the separate worktrees? I havent really seen a seamless way to approach this or do people just have the agents work on distinctly unrelated stuff? Secondly, are containers the primary sandboxing appraoch? or do you support vms?
Bnjoroge··on Show HN: ctx – an Agentic Development Environment (ADE)
because you probably need both if you are doing guided agentic work. IDE gives you the familiar benefits, especially code nav. If you are using background agents or launching agents without reviewing their work, then I guess you dont need an IDE.
Bnjoroge··on Show HN: ctx – an Agentic Development Environment (ADE)
Agree with this. I find myself switching panes between conductor or codex and zed because of code navigation. Maybe that's what cursor is trying to do in their new version, but I havent tried it yet
Bnjoroge··on Cursor 3
That philosophy wouldnt help justify the narrative for their massive valuation.
Bnjoroge··on EmDash – a spiritual successor to WordPress that solves plugin security
There's a big difference between the two. If you still think agent-guided development doesnt work well, you need to update your priors
Bnjoroge··on Don't Wait for Claude
Lots of LLM-isms in the article from a very casual scan so going to assume nothing interesting here
Bnjoroge··on Schedule tasks on the web
thats like looking for a unicorn.
← PreviousPage 5 of 9Next →